Speaker:
Professor Chris G. Willcocks
Associate Professor
Department of Computer Science, Durham University

Abstract:

There are several key equations in the generative modelling literature, most of which estimate the probability of data. Each related modelling approach (Flows, EBMs, VAEs, GANs, OT, Autoregressive,…) have trade-offs in terms of (i) modelling quality, (i) inference time/depth, and (iii) distribution coverage/mode collapse. Building off findings in our TPAMI 2022 review, “Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models”, this talk covers high-level theoretical insights into the different generative modelling paradigms, discussing where there is a gap in the current theory and looking at promising directions such as from optimal transport theory and implicit networks, to address upcoming challenges.

Biography:

Chris G. Willcocks is an associate professor in computer science at Durham University where he leads the deep learning and reinforcement learning modules. His research is in theoretical aspects of deep learning, with a particular emphasis on non-adversarial methodologies such as probabilistic diffusion models and stochastic processes. Research within his group has led to several impactful results in generative modelling including an extension of diffusion models to infinite dimensions without requiring latent vector compression, and an approach that shows you don’t need encoders in traditional autoencoders. He is a Fellow of the Higher Education Academy (FHEA), an area chair for BMVC, and has authored over 30 peer-reviewed publications in venues such as ICLR, CVPR, ECCV and TPAMI.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Dr. YANG Lin
Assistant Professor
Electrical and Computer Engineering Department, University of California

Abstract:

The success of reinforcement learning (RL) heavily depends on the approximation of functions such as policy, value, or models. Misspecification—a mismatch between the ground-truth and the best function approximators—often occurs, particularly when the ground-truth is complex. Because the misspecification error does not disappear even with an infinite number of samples, it’s crucial to design algorithms that demonstrate robustness under misspecification. In this talk, we will first present a lower bound illustrating that RL can be inefficient (e.g., possessing exponentially large complexity) if the features can only represent the optimal value functions approximately but with high precision. Subsequently, we will show that this issue can be mitigated by approximating the transition probabilities. In such a setting, we will demonstrate that both policy-based and value-based approaches can be resilient to model misspecifications. Specifically, we will show that these methods can maintain accuracy even under large, locally-bounded misspecification errors. Here, the function class might have a \Omega(1) approximation error in specific states and actions, but it remains small on average under a policy-induced state-distribution. Such robustness to model misspecification partially explains why practical algorithms perform so well, paving the way for new directions in understanding model misspecifications.

Biography:

Dr. Lin Yang is an Assistant Professor in the Electrical and Computer Engineering Department at the University of California, Los Angeles. His current research focuses on the theory and applications of reinforcement learning. Previously, he served as a postdoctoral researcher at Princeton University. He earned two Ph.D. degrees in Computer Science and in Physics & Astronomy from Johns Hopkins University. Prior to that, he obtained a Bachelor’s degree in Math & Physics from Tsinghua University. Dr. Yang has numerous publications in premier machine learning venues like ICML and NeurIPS, and has served as area chairs for these conferences. His receives an Amazon Faculty Award, a Simons-Berkeley Research Fellowship, the JHU MINDS Best Dissertation Award, and the JHU Dean Robert H. RoyFellowship.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Professor ZHANG Hong
Assistant Professor
Cheriton School of Computer Science, University of Waterloo

Abstract:

The world is undergoing a data revolution. Emerging big data and ML applications are harnessing massive volumes of data to uncover hidden patterns, correlations, and other valuable insights, transforming information and knowledge production. As the data volume keeps growing explosively, these applications require high-performance big data and ML systems to efficiently transfer, store, and process data at a massive scale.

In this talk, I advocate an application-oriented principle to design big data and ML systems: fully exploiting application-specific structures — communication patterns, execution dependencies, ML model structures, etc. — to suit application-specific performance demands. I will present how I have developed the application-oriented principle throughout my PhD-Postdoc-Faculty research, and how I have applied it to build systems tailored for different big data and ML applications.

Biography:

ZHANG Hong  is currently an assistant professor at the Cheriton School of Computer Science at the University of Waterloo. Previously, he was a postdoctoral scholar at UC Berkeley and obtained his Ph.D. degree in Computer Science and Engineering from HKUST. Hong is broadly interested in computer systems and networking, with special focuses on distributed data analytics and ML systems, data center networking, and serverless computing. His research work appeared in prestigious systems and networking conferences, such as SIGCOMM, NSDI, and EuroSys. He has been awarded the Google Ph.D. Fellowship in systems and networking.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Professor Chang Wen Chen
Chair Professor of Visual Computing
The Hong Kong Polytechnic University

Abstract:
Visual computing, traditionally, is a generic term for all computer science disciplines for algorithmic development dealing with images, videos, and other types of visual data. This talk shall focus on contemporary visual computing design from several systematic perspectives. Contemporary visual computing has been substantially advanced to enhance both human understanding and machine intelligence. The ultimate goal for human understanding will be for visual computing algorithms to generate human-like storytelling with a rational contextual setting and the capability to apply general knowledge. For machine intelligence, a more appropriate form of representing semantics from visual data will be to utilize a well-structured scene graph generation approach to characterize the logical relationship among the subjects and objects detected from the visual data. We shall report our recent research activities in developing advanced visual computing algorithms for both human understanding and machine intelligence. These exemplary applications demonstrate several unique visual computing capabilities in understanding the real world with more accurate contextual and environmental interpretations. These examples also illustrate the technical challenges we are facing and the potential impacts that contemporary visual computing systems are making, including the paradigm-shifting visual semantic communication design for the future 6G mobile networks.

Biography:

Chang Wen Chen is currently Chair Professor of Visual Computing at The Hong Kong Polytechnic University. Before his current position, he served as Dean of the School of Science and Engineering at The Chinese University of Hong Kong, Shenzhen from 2017 to 2020, and concurrently as Deputy Director at Peng Cheng Laboratory from 2018 to 2021. Previously, he has been an Empire Innovation Professor at the State University of New York at Buffalo (SUNY) from 2008 to 2021 and the Allan Henry Endowed Chair Professor at the Florida Institute of Technology from 2003 to 2007.

He has served as an Editor-in-Chief for IEEE Trans. Multimedia (2014-2016) and IEEE Trans. Circuits and Systems for Video Technology (2006-2009). He has received many professional achievement awards, including ten (10) Best Paper Awards in premier publication venues, the prestigious Alexander von Humboldt Award in 2010, the SUNY Chancellor’s Award for Excellence in Scholarship and Creative Activities in 2016, and UIUC ECE Distinguished Alumni Award in 2019. He is an IEEE Fellow, a SPIE Fellow, and a Member of the Academia Europaea.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Prof. Haohuan Fu
Professor
Department of Earth System Science, Tsinghua University

Abstract:
Defined as the fastest computers in the world by the name, supercomputers have been important tools for making scientific discoveries and technology breakthroughs. In this talk, we will introduce a series of Sunway Supercomputers, which demonstrate a superb example of integrating tens of millions of cores into a high-resolution numerical simulator or a large-scale machine learning engine, and bringing opportunities for widening our knowledge boundaries in various domains. Application examples include ultra-high-resolution climate modeling and earthquake simulation, close-to-real-time quantum circuit simulation, unsupervised learning to achieve nation-scale land cover mapping, and training large deep learning models of brain-scale complexity. Through these examples, we discuss the key issues and potential of combining supercomputing and AI technologies for solving the major challenges that we face.

Biography:
Haohuan Fu is a professor in the Department of Earth System Science, Tsinghua University, and the deputy director of the National Supercomputing Center in Wuxi. Fu has his BE (2003) in CS from Tsinghua University, MPhil (2005) in CS from City University of Hong Kong, and PhD (2009) in computing from Imperial College London. His research work focuses on supercomputing architecture and software, leading to three ACM Gordon Bell Prizes (nonhydrostatic atmospheric dynamic solver in 2016, nonlinear earthquake simulation in 2017, and random quantum circuit simulation in 2021).

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Prof. Jin-Song Dong
Professor
School of Computing, National University of Singapore

Abstract:
Sports analytics encompasses the utilization of data science, artificial intelligence (AI), psychology, and advanced Internet of Things (IoT) devices to enhance sports performance, strategy, and decision-making. This process involves the collection, processing, and interpretation of cloud-based data from a variety of sources, such as video recordings, performance metrics, and scouting reports. The resulting insights aid in evaluating player and team performance, preventing injuries, and supporting coaches and team managers in making well-informed decisions to optimize resources and achieve superior outcomes.

One widely recognized formal method, Probabilistic Model Checking (PMC), has been conventionally employed in reliability analysis for intricate safety critical systems. For instance, the reliability of an aircraft can be determined by evaluating the reliability of its individual components, including the engine, wings, and sensors. Our groundbreaking approach applies PMC to a novel domain: Sports Strategy Analytics. As an example, the reliability (winning percentage) of a sports player can be ascertained from the reliability (success rate) of their specific sub-skill sets (e.g., serve, forehand, backhand, etc., in tennis).

In this presentation, we will discuss our recent research work, which involves the application of PMC, machine learning, and computer vision to the realm of sports strategy analytics. At the end of the presentation, we will also discuss the vision of a new international sports analytics conference series (https://formal-analysis.com/isace/2023/).

Biography:
Jin-Song Dong is a professor at the National University of Singapore. His research spans a range of fields, including formal methods, safety and security systems, probabilistic reasoning, sports analytics, and trusted machine learning. He co-founded the commercialized PAT verification system, which has garnered thousands of registered users from over 150 countries and received the 20-Year ICFEM Most Influential System Award. Jin Song also co-founded the commercialized trusted machine learning system Silas (www.depintel.com). He has received numerous best paper awards, including the ACM SIGSOFT Distinguished Paper Award at ICSE 2020.

He served on the editorial board of ACM Transactions on Software Engineering and Methodology, Formal Aspects of Computing, and Innovations in Systems and Software Engineering, A NASA Journal. He has successfully supervised 28 PhD students, many of whom have become tenured faculty members at leading universities worldwide. He is also a Fellow of the Institute of Engineers Australia. In his leisure time, Jin Song developed Markov Decision Process (MDP) models for tennis strategy analysis using PAT, assisting professional players with pre-match analysis (outperforming the world’s best). He is a Junior Grand Slam coach and takes pleasure in coaching tennis to his three children, all of whom have reached the #1 national junior ranking in Singapore/Australia. Two of his children have earned NCAA Division 1 full scholarships, while his second son, Chen Dong, played #1 singles for Australia in the Junior Davis Cup and participated in both the Australian Open and US Open Junior Grand Slams.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Dr. CHENG Yu
Microsoft Research Redmond, USA

Abstract:

In recent years, we are witnessing a paradigm shift where foundational models, such as GPT-4, ChatGPT, and Codex, are consolidating into fewer, but extremely large models that cover multiple modalities and tasks and significantly surpass the performance of standalone models. However, these extremely large models are still very expensive to adapt to new scenarios/tasks, deploy in the runtime inference in real-world applications, and are vulnerable to crafted adversarial examples. In this talk, I will present the techniques we developed to enable foundation models to smoothly scale to small computational footprints/new tasks, and be robust to handle diverse/adversarial textual inputs. The talk also introduces how to productionize these techniques in several applications such as Github Copliot and New Bing.

Biography:

Dr. CHENG Yu is a Principal Researcher at Microsoft Research and an Adjunct Professor at Rice University/Renmin University of China. Before joining Microsoft, he was a Research Staff Member at IBM Research & MIT-IBM Watson AI Lab. He got a Ph.D. from Northwestern University in 2015 and a bachelor’s degree from Tsinghua University in 2010. His research covers deep learning in general, with specific interests in model compression and efficiency, deep generative models, and adversarial robustness. Yu has led several teams and productized these techniques for Microsoft-OpenAI core products (e.g., Copilot, DALL-E-2, ChatGPT, GPT-4). He serves (or, has served) as an area chair for CVPR, NeurIPS, AAAI, IJCAI, ACMMM, WACV, and ECCV.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Prof. Qirun Zhang
Assistant Professor
School of Computer Science, Georgia Institute of Technology

Abstract:

Program analysis automatically reasons about program runtime behavior and provides mechanisms to determine whether a program’s execution will satisfy certain properties. Program analysis offers a rich spectrum of methods for improving software reliability. A variety of program analysis problems can be formulated as graph reachability problems in edge-labeled graphs. Over the years, we have witnessed the tremendous success of various graph-reachability-based program-analysis techniques. In this talk, I will discuss our work, in the past three years, on CFL-reachability, Dyck-reachability, and InterDyck-reachability.

Biography:

Qirun Zhang is an Assistant Professor in Computer Science at Georgia Tech. His general research interests are in programming languages and software engineering, focusing on developing new static program analysis frameworks to improve software reliability. He has received a PLDI 2020 Distinguished Paper Award, an OOPSLA 2022 Distinguished Artifact award, an NSF CAREER Award, and an Amazon Research Award in Automated Reasoning. He served on the program committees of FSE, ICSE, ISSTA, OOPSLA, PLDI, and POPL.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Prof. CAI Jianfei
Professor
Faculty of IT, Monash University

Abstract:

Neural Radiance Fields (NeRF) has been a new paradigm for 3D representation, providing implicit shape information and view-dependent appearance simultaneously. Based on this new representation, seminal 3D generation approaches have been proposed that aim to generate photorealistic images from a given distribution in a 3D-aware and view-consistent manner, while their performance in 3D geometry reconstruction is limited. On the other hand, several works demonstrate that rendering neural implicit surfaces, where gradients are concentrated around surface regions, is able to produce a high-quality 3D reconstruction. However, they focus only on holistic scene representation yet ignore individual objects inside it, thus limiting potential downstream applications. In this talk, we will first present our recent ECCV’22 work, ObjectSDF, which provides a nice object-compositional neural implicit surfaces framework that can jointly reconstruct the scene and objects inside it with only semantic masks. We will also introduce our another ECCV’22 work that can reconstruct a 3D scene modelled by NeRF, conditioned on one single-view semantic mask as input. Finally, we will provide some future directions on this topic.

Biography:

CAI Jianfei is a Professor at Faculty of IT, Monash University, where he currently serves as the Head for the Data Science & AI Department. He is also a visiting professor at Nanyang Technological University (NTU). Before that, he was Head of Visual and Interactive Computing Division and Head of Computer Communications Division in NTU. His major research interests include computer vision, deep learning and multimedia. He has successfully trained 30+ PhD students with three getting NTU SCSE Outstanding PhD thesis award. Many of his PhD students joined leading IT companies such as Facebook, Apple, Amazon, and Adobe or become faculty members in reputable universities. He is a co-recipient of paper awards in ACCV, ICCM, IEEE ICIP and MMSP. He serves or has served as an Associate Editor for IJCV, IEEE T-IP, T-MM, and T-CSVT as well as serving as Area Chair for CVPR, ICCV, ECCV, IJCAI, ACM Multimedia, ICME and ICIP. He was the Chair of IEEE CAS VSPC-TC during 2016-2018. He had also served as the leading TPC Chair for IEEE ICME 2012 and the best paper award committee chair & co-chair for IEEE T-MM 2020 & 2019. He will be the leading general chair for ACM Multimedia 2024. He is a Fellow of IEEE.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Mr. SHE Dongdong
PhD candidate
Department of Computer Science, Columbia University

Abstract:

Security vulnerabilities significantly impact our daily lives, from ransomware attacks costing billions of dollars every year to confidential data leakage in government, military and industry. Fuzzing is a popular automated technique to catch these vulnerabilities in real-world programs. Despite the wide application in industry, existing fuzzers heavily rely on rule-based designs (i.e., incorporating a set of static rules and heuristics). These fixed rules and heuristics often fail on diverse programs and severely limit fuzzing performance.

In this talk, I will present a novel and pioneering approach to general fuzzing: a data-driven approach. Fuzzing is an iterative process. Data-driven approach extracts useful knowledge from the massive amount of iterations in fuzzing and uses the learned knowledge to perform future fuzzing smartly. Meanwhile, in a data-driven approach, we can formulate fuzzing as a data-centric problem, thus bridging the connection between fuzzing to various domains (e.g., machine learning, optimization and social network), enabling adaptive and effective designs in the general fuzzing framework.

Biography:
SHE Dongdong is a PhD candidate in Computer Science at Columbia University. His research focuses on security and machine learning, particularly applying machine learning and other data-driven approaches to security problems. His work has been published at top-tier security and software engineering conferences (S&P, CCS, Security and FSE). He is the recipient of an ACM CCS Best Paper runner-up award and a finalist in the NYU CSAW applied research competition. Before attending Columbia, he obtained a Master’s in Computer Science from UC, Riverside and Bachelor’s in Electronic and Information Engineering from HUST.

Join Zoom Meeting:
https://cuhk.zoom.us/j/92596540594?pwd=bEJKc0RlN3hXQVFNTWpmcWRmVnRFdz09
Meeting ID: 925 9654 0594
Passcode: 202300

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. Renyuan Zhang
Associate Professor
Nara Institute of Science and Technology

Abstract:

This talk aims at introducing the multi-grained re-configurable computing platforms which are elastic in both of space and time domains. As the preliminary, several approximate computing technologies by Prof. Zhang’s group are introduced for efficiently accelerating the AI tasks. For the next generation of AI platforms, it is expected to explore the disruptive computer architectures for ultra-high speed, low cost, and flexible tensor computations without any benefitting of Moore’s Law. For this purpose, temporal-spatial re-configurable accelerators are demanded: (1) an innovative mechanism for data processing is explored by the snapshot (or accumulative, optionally) observation of spiking (addressing time-elastic); (2) the multi-grained re-configurable architecture is developed on the basis of our novel neural network topology seen as “DiaNet” (addressing space-elastic).

Biography:

Prof. Renyuan Zhang (Senior Member, IEEE) received the M.E. degree from Waseda University, in 2010, and the Ph.D. degree from The University of Tokyo, in 2013. He was an Assistant Professor with the Japan Advanced Institute of Science and Technology, from 2013 to 2017. He has been an Assistant Professor and an Associate Professor with the Nara Institute of Science and Technology, since 2017 and 2021, respectively. His research interests include analog–digital mixed circuits and approximate computing. He is a member of IEICE.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Dr. Xiaoxiao Li,
Assistant Professor
Department of Electrical and Computer Engineering
The University of British Columbia (UBC)

Abstract:

Federated learning (FL) is a trending framework to enable multi-institutional collaboration in machine learning without sharing raw data. This presentation will discuss our ongoing progress in designing FL algorithms that embrace the data heterogeneity properties for distributed data analysis in the FL setting. First, I will present our work on theoretically understanding FL training convergence and generalization using a neural tangent kernel, called FL-NTK. Then, I will present our algorithms for tackling data heterogeneity (on features and labels) and device heterogeneity, motivated by our previous theoretical foundation. Lastly, I will also show the promising results of applying our FL algorithms in real-world applications.

Biography:

Dr. Xiaoxiao Li is an Assistant Professor at the Department of Electrical and Computer Engineering at The University of British Columbia (UBC) starting August 2021. In addition, Dr. Li is an adjunct Assistant Professor at Yale University. Before joining UBC, Dr. Li was a Postdoc Research Fellow at Princeton University. Dr. Li obtained her Ph.D. degree from Yale University in 2020. Dr. Li’s research focuses on developing theoretical and practical solutions for enhancing the trustworthiness of AI systems in healthcare. Specifically, her recent research has been dedicated to advancing federated learning techniques and their applications in the medical field. Dr. Li’s work has been recognized with numerous publications in top-tier machine learning conferences and journals, including NeurIPS, ICML, ICLR, MICCAI, IPMI, ECCV, TMI, TNNLS, Medical Image Analysis, and Nature Methods.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Professor Yuqun Zhang
Assistant Professor
Department of Computer Science and Engineering
Southern University of Science and Technology

Abstract:

Fuzzing (or fuzz testing) refers to inputting invalid, unexpected, or random data to programs for exposing unexpected program behaviors (such as crashes, failing assertions, or memory leaks), which can be further inspected or analyzed to detect potential vulnerabilities/bugs. While recently there is a growing trend to propose new fuzzing techniques, limited attentions have been paid on studying their common/representative strategies, e.g., exploring why and how exactly their strategies work. In this talk, I will discuss a rather common fuzzing strategy, namely Havoc, which randomly mutates seeds via a mutator stacking mechanism and is widely adopted in coverage-guided fuzzers. I will show that essentially, it is Havoc which dominates the fuzzing effectiveness, including increasing coverage and exposing program bugs, rather than the strategies proposed by the coverage-guided fuzzers. Moreover, it can be rather simple to enhance the effectiveness of Havoc.

Biography:

Yuqun Zhang is an Assistant Professor in the Department of Computer Science and Engineering at Southern University of Science and Technology, Shenzhen, China. His research focuses on exploring new general-purpose and domain-specific quality assurance methods for software. His research output on fuzzing and taint analysis has been deployed in Tencent and Alibaba to successfully detect hundreds of bugs/vulnerabilities. He received his PhD from UT Austin. He has been awarded one ACM SIGSOFT Distinguished Paper Award as well as one nominee.

Enquiries: Mr Jeff Liu (jeffliu@cse.cuhk.edu.hk)

6 lab managers from Huawei Cloud will hold a presentation and communication session in the Room 121, HSH Engineering Building at the Chinese University of Hong Kong on March 30th, from 10 – 11 am. They will introduce the following six innovative Labs from Huawei Cloud:

1. Algorithm Innovation Lab: Application of mathematical modeling and optimization algorithms in Huawei Cloud, presented by Dr. Wenli Zhou.
2. Cloud Storage Innovation Lab: Introduction to building a high-performance, highly reliable, secure, and intelligent cloud-native storage platform (research areas include key technologies and core algorithms in block storage, object storage, file storage, memory storage, etc., including distributed data consistency, space management, metadata indexing, intelligent caching, etc.), presented by Dr. Xusheng Chen.
3. Data Intelligence Innovation Lab: Provide right data to the right person at the right time, presented by Dr. Ke Xu.
4. Availability Engineering Lab: Introduction to the related technologies of public cloud and large-scale distributed application architecture reliability and availability engineering, technology, and innovation capabilities center, presented by Ling Wei.
5. Computing and Networking Innovation Lab: In the computing domain, focus on tapping the efficiency of large-scale computing resource reuse in Huawei Cloud + continuous research on next-generation autonomous cloud network systems in the networking domain, presented by Dr. Zengyin Yang.
6. Cloud Database Innovation Lab: Innovating Cloud-Native Databases for Next-Gen Applications, presented by Dr. Hao Zhang.

Lab Introduction:

The Computing and Networking Innovation Lab focuses on the research and development of new computing and networking in Huawei Cloud. Positioned as a technical pre-research team for Huawei Cloud, it mainly studies two major areas of cloud computing:
-In the computing domain, focus on tapping the efficiency of large-scale computing resource reuse in Huawei Cloud, including cloud service application load profiling, VM/container scheduling algorithms and systems, real-time QoS detection and control systems, and new research directions in virtualization -In the networking domain, based on the requirements and data of cloud computing itself, continuously research the next-generation autonomous cloud network system, including the next-generation gateway platform, P4/NP programmable device platform, network brain combined with AI, large-scale high-performance SDN platform, real-time network measurement and verification, and other new cloud computing network directions.

The Cloud Storage Innovation Lab is Huawei Cloud’s storage innovation research center. The research areas involve key technologies and core algorithms in block storage, object storage, file storage, memory storage, etc., including distributed data consistency, space management, metadata indexing, intelligent caching, etc. It is committed to building a high-performance, highly reliable, secure, and intelligent cloud-native storage platform, providing the best experience and cost-effective storage services for enterprises moving to the cloud.

Enquiries: Professor Michael LYU (lyu@cse.cuhk.edu.hk) / Jeff Liu (jeffliu@cse.cuhk.edu.hk)

Speaker:
Professor Yibo Lin
Assistant Professor
School of Integrated Circuits
Peking University

Abstract:

Physical design is a critical step in the design flow of modern VLSI circuits. With continuous increase of design complexity, physical design becomes extremely challenging and time-consuming due to the repeated design iterations for the optimization of performance, power, and area. With recent boom of artificial intelligence, deep learning has shown its potential in various fields, like computer vision, recommendation systems, robotics, etc. Incorporating deep learning into the VLSI design flow has also become a promising trend. In this talk, we will introduce our recent studies on developing dedicated deep learning techniques for cross-stage modeling and optimization in physical design. We will also discuss the impact of large-scale and diverse datasets (e.g., CircuitNet) on improving the performance of deep learning models.

Biography:

Yibo Lin is an assistant professor in the School of Integrated Circuits at Peking University. He received the B.S. degree in microelectronics from Shanghai Jiaotong University in 2013, and his Ph.D. degree from the Electrical and Computer Engineering Department of the University of Texas at Austin in 2018. His research interests include physical design, machine learning applications, and GPU/FPGA acceleration. He has received 6 Best Paper Awards at premier venues including DATE 2022, TCAD 2021, and DAC 2019. He has also served in the Technical Program Committees of many major conferences, including ICCAD, ICCD, ISPD, and DAC.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Mr. DING Kaize

Abstract:

The world around us — and our understanding of it — is rich in relational structure: from atoms and their interactions to objects and entities in our environments. Graphs, with nodes representing entities and edges representing relationships between entities, serve as a common language to model complex, relational, and heterogeneous systems. Despite the success of recent deep graph learning, the efficacy of existing efforts heavily depends on the ideal data quality of the observed graphs and the sufficiency of the supervision signals provided by the human-annotated labels, leading to the fact that those carefully designed models easily fail in resource-constrained scenarios.

In this talk, I will present my recent research contributions centered around data-efficient learning for relational and heterogeneous graph-structured data. First, I will introduce what data-efficient graph learning is and my contributions to different research problems under its umbrella, including graph few-shot learning, graph weakly-supervised learning, and graph self-supervised learning. Based on my work, I will elucidate how to push forward the performance boundary of graph learning models especially graph neural networks with minimal human supervision signals. I will also touch upon the applications of data-efficient graph learning to different domains and finally conclude my talk with a brief overview of my future research agenda.

Biography:

DING Kaize is currently a Ph.D. candidate from the School of Computing and Augmented Intelligence (SCAI) at Arizona State University (ASU). Kaize is working at the Data Mining and Machine Learning (DMML) Lab with Prof. Huan Liu and previously he was previously interned at Google Brain, Microsoft Research, and Amazon Alexa AI. Kaize is broadly interested in the areas of data mining, machine learning, and natural language processing and their interdisciplinary applications in different domains including cybersecurity, social good, and healthcare. His recent research interests particularly focus on data-efficient learning and graph neural networks. He has published a series of papers in top conferences and journals such as AAAI, EMNLP, IJCAI, KDD, NeurIPS, and TheWebConf. Kaize was the recipient of the ASU Graduate College Completion Fellowship and ASU GPSA Outstanding Research Award, etc. More information about him can be found at https://www.public.asu.edu/~kding9/ .

Join Zoom Meeting:
https://cuhk.zoom.us/j/99778568306?pwd=Nms0cm9takVNQWtRaDhuaVdaTVJ5dz09

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Professor Jeff Kramer
Emeritus Professor, Department of Computing,
Imperial College London

Abstract:

Change in complex systems is inevitable. Providing rigorous techniques and tools to support dynamic system adaptation so that it can be performed online, at runtime, is certainly challenging. However the potential resilience rewards could be great. There is the need for a software architecture and runtime support for dynamic software configuration, plan execution and plan synthesis, domain environment modelling and monitoring, and ultimately even potentially performing some elements of requirements engineering at runtime! This talk will present our motivation and vision, describing our work to date and our hopes for the future.

Biography:

Jeff Kramer is Emeritus Professor of Computing at Imperial College London.

His research work is primarily concerned with software engineering, with particular emphasis on evolving software architectures, behaviour analysis, the use of models in requirements elaboration and self organising adaptive software systems. An early research result was the DARWIN language for evolving distributed architectures, and more recently was the Three Layer Model for self-adaptive systems. One of the major research challenges in self-managed adaptation is the need to perform requirements analysis at runtime.

Jeff has been involved in many major conferences and journals, notably as program co-chair of ICSE in Los Angeles in 1999, general co-chair of ICSE 2010 in Cape Town, and Editor in Chief of IEEE TSE from 2006 to 2010. His awards include the 2005 ACM SIGSOFT Outstanding Research Award and the 2011 ACM SIGSOFT Distinguished Service. He is a Fellow of the Royal Academy of Engineering, Fellow of the ACM, and a Member of Academia Europaea.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Mr. NIE Pengyu

Abstract:

Machine Learning (ML) techniques have been increasing adopted for Software Engineering (SE) tasks, such as code completion and code summarization. However, existing ML models provide limited value for SE tasks, because these models do not take into account the key characteristics of software: software is executable and software constantly evolves. In this talk, I will present my insights and work on developing execution-guided and evolution-aware ML models for several SE tasks targeting important domains, including software testing, verification, and maintenance.

First, I will present my techniques to help developers write tests and formal proofs. My work has direct impact on software correctness and everyone that depends on software. I will present TeCo: the first ML model for test completion/generation, and Roosterize: the first model for lemma name generation. In order to achieve good performance, these two tasks require reasoning about code execution, which existing ML models are not capable of. To tackle this problem, I designed and develop ML models that integrate execution data and use such data to validate generation results.

Next, I will present my techniques to help developers maintain software. Specifically, I will present my work on comment updating, i.e., automatically updating comments when associated code changes. I proposed the first edit ML model for SE to solve this task, which learns to perform developer-like edits instead of generating comments from scratch. This model can be generalized for general-purpose software editing, including tasks such as bug fixing and automated code review.

All my code and data are open-sourced, evaluated on real-world software, and shown to outperform existing ML models by large margins. My contributions lay the foundation for the development of accurate, robust, and interpretable ML models for SE.

Biography:
NIE Pengyu is a Ph.D. candidate at the University of Texas at Austin, advised by Milos Gligoric. Pengyu obtained his Bachelor’s Degree at the University of Science and Technology of China. His research area is the fusion of Software Engineering (SE) and Natural Language Processing (NLP), with a focus on improving developers’ productivity during software development, testing, and maintenance. He has published 14 papers in top-tier SE, NLP, and PL conferences. He is the recipient of an ACM SIGSOFT Distinguished Paper Award (FSE 2019), and the UT Austin Graduate School Continuing Fellowship. More information can be found on his webpage: https://pengyunie.github.io.

Join Zoom Meeting:
https://cuhk.zoom.us/j/95560110806?pwd=VFN4eXc2UU1KOTJIVk15aGU2ZkVydz09
Meeting ID: 955 6011 0806
Passcode: 202300

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. ZHAO Xiangyu
Assistant Professor, School of Data Science
City University of Hong Kong (CityU)

Abstract:

Deep recommender systems have become increasingly popular in recent years, and have been utilized in a variety of domains, including movies, music, books, search queries, and social networks. They assist users in their information-seeking tasks by suggesting items (products, services, or information) that best fit their needs and preferences. Most existing recommender systems are based on static recommendation policies and hand-crafted architectures. Specifically, (i) most recommender systems consider the recommendation procedure as a static process, which may fail given the dynamic nature of the users’ preferences; (ii) existing recommendation policies aim to maximize the immediate reward from users, while completely overlooking their long-term impacts on user experience; (iii) designing architectures manually requires ample expert knowledge, non-trivial time and engineering efforts, while sometimes human error and bias can lead to suboptimal architectures. I will introduce my efforts in tackling these challenges via reinforcement learning (RL) and automated machine learning (AutoML), which can (i) adaptively update the recommendation policies, (ii) optimize the long-term user experience, and (iii) automatically design the deep architectures for recommender systems.

Biography:

Prof. Xiangyu ZHAO is an assistant professor of the school of data science at City University of Hong Kong (CityU). His current research interests include data mining and machine learning, and their applications in Recommender System, Smart City, Healthcare, Carbon Neutral and Finance. He has published more than 60 papers in top conferences (e.g., KDD, WWW, AAAI, SIGIR, IJCAI, ICDE, CIKM, ICDM, WSDM, RecSys, ICLR) and journals (e.g., TOIS, SIGKDD, SIGWeb, EPL, APS). His research has been awarded ICDM’22 and ICDM’21 Best-ranked Papers, Global Top 100 Chinese New Stars in AI, CCF-Ant Research Fund, CCF-Tencent Open Fund, Criteo Faculty Research Award, Bytedance Research Collaboration Award, and nomination for Joint AAAI/ACM SIGAI Doctoral Dissertation Award. He serves as top data science conference (senior) program committee members and session chairs, and journal guest editors and reviewers. He serves as the organizers of DRL4KDD@KDD’19/WWW’21 and DRL4IR@SIGIR’20/21/22 and a lead tutor at WWW’21/22/23, IJCAI’21 and WSDM’23. He also serves as the founding academic committee members of MLNLP, the largest Chinese AI community with millions of members/followers. The models and algorithms from his research have been launched in the online system of many companies. Please find more information at https://zhaoxyai.github.io/.

Join Zoom Meeting:
https://cuhk.zoom.us/j/96382199967
Meeting ID: 963 8219 9967

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Mr. ZHANG Hanrui

Abstract:

Machine learning algorithms now play a major part in all kinds of decision-making scenarios. When the stakes are high, self-interested agents — about whom decisions are being made — are increasingly tempted to manipulate the machine learning algorithm, in order to better fulfill their own goals, which are generally different from the decision maker’s. This highlights the importance of making machine learning algorithms robust against manipulation. In this talk, I will focus on generalization (i.e., the bridge between training and testing) in strategic classification: Traditional wisdom suggests that a classifier trained on historical observations (i.e., the training set) usually also works well on future data points to be classified (i.e., the test set). I will show how this very general principle fails when agents being classified strategically respond to the classifier, and present an intuitive fix that leads to provable (and in fact, optimal) generalization guarantees under strategic manipulation. I will then discuss the role of incentive-compatibility in strategic classification, and present experimental results that illustrate how the theoretical results can guide practice. If time permits, I will also discuss distinguishing strategic agents with samples, and/or dynamic decision making with strategic agents.

Biography:
ZHANG Hanrui is a PhD student at Carnegie Mellon University, advised by Vincent Conitzer. He was named a finalist for the 2021 Facebook Fellowship. His work won the Best Student Paper Award at the European Symposia on Algorithms (ESA), and a Honorable Mention for Best Paper Award at the AAAI Conference on Human Computation and Crowdsourcing (HCOMP). He received his bachelor’s degree in Yao’s Class, Tsinghua University, where he won the Outstanding Undergraduate Thesis Award.

Join Zoom Meeting:
https://cuhk.zoom.us/j/96485699602?pwd=aXZZd0Z4aDVzVjhWdTRiVGt5cytvdz09
Meeting ID: 964 8569 9602
Passcode: 202300

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Mr. ZHOU Dongruo

Abstract:

Reinforcement learning (RL) has achieved great empirical success in many real-world problems in the last few years. However, many RL algorithms are inefficient due to their data-hungry nature. Whether there exists a universal way to improve the efficiency of existing RL algorithms remains an open question.

In this talk, I will give a selective overview of my research, which suggests that efficient (and optimal) RL can be built through the lens of uncertainties. I will show that uncertainties can not only guide RL to make decisions efficiently, but also have the ability to accelerate the learning of the optimal policy over a finite number of data samples collected from the unknown environment. By utilizing the proposed uncertainty-based framework, I design computationally efficient and statistically optimal RL algorithms under various settings, which improve existing baseline algorithms from both theoretical and empirical aspects. At the end of this talk, I will briefly discuss several additional works, and my future research plan for designing next-generation decision making algorithms.

Biography:
ZHOU Dongruo is a final-year PhD student in the Department of Computer Science at UCLA, advised by Prof. Quanquan Gu. His research is broadly on the foundation of machine learning, with a particular focus on reinforcement learning and stochastic optimization. He aims to provide a theoretical understanding of machine learning methods, as well as to develop new machine learning algorithms with better performance. He is a recipient of the UCLA dissertation year fellowship.

Join Zoom Meeting:
https://cuhk.zoom.us/j/93549469461?pwd=R0FOaFdxOG5LS0s2Q1RmaFdNVm4zZz09
Meeting ID: 935 4946 9461
Passcode: 202300

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Mr. Shi QIU

Abstract:

As a fundamental 3D data representation, point clouds can be easily collected using 3D scanners, retaining abundant information for AI-driven applications such as autonomous driving, virtual/augmented reality, and robotics. Given the prominence of deep neural networks in current days, deep learning-based point cloud data understanding is playing an essential role in 3D computer vision research.

In this seminar, we focus on learning deep feature representations of point clouds for 3D data processing and analysis. Basically, we start from investigating low-level vision problems of 3D point clouds, which helps to comprehend and deal with the inherent sparsity, irregularity and unorderedness of this 3D data type. On this front, we introduce a novel transformer-based model that fully utilizes the dependencies between scattered points for high-fidelity point cloud upsampling. Moreover, we deeply explore high-level vision problems of point cloud analysis, including the classification, segmentation and detection tasks. Specifically, we propose to (i) learn more geometric information for accurate point cloud classification, (ii) exploit dense-resolution features to recognize small-scale point clouds, (iii) augment local context for large-scale point cloud analysis, and (iv) refine the basic point feature representations for benefiting various point cloud recognition problems and different baseline models. By conducting comprehensive experiments, ablation studies and visualizations, we quantitatively and qualitatively demonstrate our contributions in the deep learning-based research of 3D point clouds.

In general, this seminar presents a review of deep learning-based 3D point cloud research, introduces our contributions in learning deep feature representations of point cloud data, and proposes research directions for future work. We expect this seminar to inspire further exploration into 3D computer vision and its applications.

Biography:
Shi Qiu is a PhD candidate at Australian National University and a postgraduate researcher at Data61-CSIRO. Previously, he obtained his bachelor degree of Electronic Engineering from Dalian University of Technology in 2015, and master degrees of Digital Media Technology from KTH and UCL in 2017. His main research interests are in 3D computer vision and virtual/augmented reality, where he has authored a few research papers in top venues including T-PAMI, CVPR, etc. In addition to academic research, he also interned at industry-based labs including Vivo AI Lab and Tencent’s XR Vision Labs. He is a recipient of scholarships funded by China, EU, and Australia.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. Kazushi Ikeda
Nara Institute of Science and Technology (NAIST)

Abstract:

In this talk, I introduce some studies in Mathematical Informatics Lab, NAIST. Mathematical models are a strong tool in science to describe the nature. However, they are also useful in engineering or even in computation. One example of the math models is the deep learning theory. In deep learning, so many techniques, such as drop-out and skip connections, have been proposed but their effectiveness is not clear. We analyzed it by considering their geometrical meaning.  I show other examples in science and engineering in our projects.

Biography:
Kazushi Ikeda got his B.E., M.E., and Ph.D. in Mathematical Engineering from University of Tokyo in 1989, 1991, and 1994. He joined Kanazawa University as an assistant professor in 1994 and became a junior/senior associate professor of Kyoto University in 1998 and 2003, respectively. He has been a full professor of NAIST since 2008.
He was a research associate of CUHK for two months in 1995.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. MENG Wei
Assistant Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

Abstract:

The Internet has powered a large variety of important services and applications, such as search, social networking, banking and shopping. Because of their increasing importance, the applications and their huge number of users on the Internet have become the primary targets of cyber attacks and abuses. However, the dynamic nature of the complex modern software makes it very difficult to reason about the security of those applications, especially by using static program analysis techniques.

In this talk, I will share my experience in understanding and improving application security with dynamic program analysis approaches. I will illustrate it with two representative works that address two emerging threats. First, I will introduce how we investigated click interception on the web with a dynamic JavaScript monitoring system. Second, I will present how we combined static analysis and dynamic analysis to accurately detect algorithmic complexity vulnerabilities. Finally, I will discuss about the other challenges and opportunities for further securing software applications.

Biography:
Wei Meng is an Assistant Professor in the Department of Computer Science and Engineering, The Chinese University of Hong Kong.   His main research interests are in computer security and privacy. He designs and builds systems to protect end users and applications on the Internet. His research has been published primarily at top conferences such as IEEE S&P, USENIX Security, CCS, WWW, and ESEC/FSE. He received his Ph.D. degree in Computer Science from the Georgia Institute of Technology in 2017 and his Bachelor’s degree in Computer Science and Technology from Tsinghua University in 2012. He currently leads the CUHK Computer Security Lab in the CSE department.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. YANG Ming-Chang
Assistant Professor
Department of Computer Science and Engineering
The Chinese University of Hong Kong

Abstract:
In light of technological advancement over the last few decades, there have been many revolutionary developments in memory and storage technologies. Nevertheless, though these emerging technologies offer us new design choices and trade-offs, deploying them in modern memory and storage systems is non-trivial and challenging. In this talk, I will first summarize our efforts in embracing the cutting-edge technologies in memory and storage systems through co-designing the hardware and software. To make a case, I will present two of our recent studies: one in delivering a scalable, efficient and predictable hashing on the persistent memory (PM) technology and the other in constructing a cost-effective yet high-throughput persistent key-value store on the latest hard disk technology called interlaced magnetic recording (IMR). Finally, I will highlight some new promising memory/storage technologies that may pave new paths for and even completely revolutionize the upcoming computer systems.

Biography:
Ming-Chang Yang is currently an Assistant Professor at the Department of Computer Science and Engineering, The Chinese University of Hong Kong. He received his B.S. degree from the Department of Computer Science at National Chiao-Tung University, Taiwan, in 2010. He received his Master and Ph.D. degrees from the Department of Computer Science and Information Engineering at National Taiwan University, Taiwan, in 2012 and 2016, respectively. He now serves as an Associate Editor in ACM Transactions on Cyber-Physical Systems (TCPS). Also, he served as a TPC co-chair for NVMSA 2021 and as a TPC member for several major conferences. In addition, he received 2 best paper awards from the prestigious conferences in his field (including ACM/IEEE ISLPED 2020 and IEEE NVMSA 2019). His primary research interests include the emerging non-volatile memory and storage technologies, memory and storage systems, and the next-generation memory/storage architecture designs. For details, please refer to his personal homepage: http://www.cse.cuhk.edu.hk/~mcyang/

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. WONG Chi-Wing Raymond
Professor
Department of Computer Science and Engineering
The Hong Kong University of Science and Technology

Abstract:
When faced with a database containing millions of tuples, an end user might be only interested in finding his/her favorite tuple in the database. In this talk, we study how to help an end user to find such a favorite tuple with a few user interations. In each interaction, a user is presented with a small number of tuples (which can be artificial tuples outside the database or true tuples inside the database) and s/he is asked to indicate the tuple s/he favors the most among them.

Different from the previous work which displays artificial tuples to users during the interaction and requires heavy user interactions, we achieve a stronger result. Specifically, we use a concept, called the utility hyperplane, to model the user preference and an effective pruning strategy to locate the favorite tuple for a user in the whole database. Based on these techniques, we developed an interactive system, called FindYourFavorite, and demonstrate that the system could identify the favorite tuple for a user with a few user interactions by always displaying true tuples in the database.

Biography:
Raymond Chi-Wing Wong is a Professor in Computer Science and Engineering (CSE) of The Hong Kong University of Science and Technology (HKUST). He is currently the associate head of Department of Computer Science and Engineering (CSE). He was the associate director of the Data Science & Technology (DSCT) program (from 2019 to 2021), the director of the Risk Management and Business Intelligence (RMBI) program (from 2017 to 2019), the director of the Computer Engineering (CPEG) program (from 2014 to 2016) and the associate director of the Computer Engineering (CPEG) program (from 2012 to 2014). He received the BSc, MPhil and PhD degrees in Computer Science and Engineering in the Chinese University of Hong Kong (CUHK) in 2002, 2004 and 2008, respectively. In 2004-2005, he worked as a research and development assistant under an R&D project funded by ITF and a local industrial company called Lifewood.

He received 38 awards. He published 104 conference papers (e.g., SIGMOD, SIGKDD, VLDB, ICDE and ICDM), 38 journal/chapter papers (e.g., TODS, DAMI, TKDE, VLDB journal and TKDD) and 1 book. He reviewed papers from conferences and journals related to data mining and database, including VLDB conference, SIGMOD, TODS, VLDB Journal, TKDE, TKDD, ICDE, SIGKDD, ICDM, DAMI, DaWaK, PAKDD, EDBT and IJDWM. He is a program committee member of conferences, including SIGMOD, VLDB, ICDE, KDD, ICDM and SDM, and a referee of journals, including TODS, VLDBJ, TKDE, TKDD, DAMI and KAIS.

His research interests include database, data mining and artificial intelligence.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. Hervé Lombaert
Associate Professor
ETS Montreal, Canada

Abstract:
How to analyze the shapes of complex organs, such as the highly folded surface of the brain? This talk will show how spectral shape analysis can benefit general learning problems where data fundamentally lives on surfaces. We exploit spectral coordinates derived from the Laplacian eigenfunctions of shapes. Spectral coordinates have the advantage over Euclidean coordinates, to be geometry aware, invariant to isometric deformations, and to parameterize surfaces explicitly. This change of paradigm, from Euclidean to spectral representations, enables a classifier to be applied *directly* on surface data, via spectral coordinates. Brain matching and learning of surface data will be shown as examples. The talk will focus, first, on the spectral representations of shapes, with an example on brain surface matching; second, on the basics of geometric deep learning; and finally, on the learning of surface data, with an example on automatic brain surface parcellation.

Biography:
Hervé Lombaert (和偉 隆巴特/和伟 隆巴特) is an Associate Professor at ETS Montreal, Canada, where he holds a Canada Research Chair in Shape Analysis in Medical Imaging. His research focuses on the statistics and analysis of shapes in the context of machine learning and medical imaging. His work on graph analysis has impacted the performance of several applications in medical imaging, from the early image segmentation techniques with graph cuts, to recent surface analysis with spectral graph theory and graph convolutional networks. Hervé has authored over 70 papers, 5 patents, and earned several awards, such as the IPMI Erbsmann Prize. He had the chance to work in multiple centers, including Inria Sophia-Antipolis (France), Microsoft Research (Cambridge, UK), Siemens Corporate Research (Princeton, NJ), McGill University (Canada), and the University of Montreal (Canada).

More at: https://profs.etsmtl.ca/hlombaert

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. QIN Jing
Centre for Smart Health
School of Nursing
The Hong Kong Polytechnic University

Abstract:
Deep learning has achieved remarkable success in various medical image analysis tasks. No matter the past, present, or the foreseeable future, one of the main obstacles that prohibits deep learning models from being successfully developed and deployed in clinical settings is the scarcity of training data. In this talk, we shall review, as well as rethink, our long experience in investigating how to enhance representation capability of deep learning models to achieve satisfactory performance under limited training data. Based on our experience, we attempt to identify and sort out the evolution trajectory of applying deep leaning to medical image analysis, somehow reflecting the development path of deep learning itself beyond the context of our specific applications. The models we developed, at least in our experience, are both effects and causes: effects of the clinical challenges we faced and the technical frontiers at that time; causes, if they are really useful and inspiring, of following more advanced models that are capable of addressing their limitations. To the end, by rethinking such an evolution, we can identify some future directions that deserve to be further studied.

Biography:
QIN, Jing (Harry) is currently an associate professor in Centre for Smart Health, School of Nursing, The Hong Kong Polytechnic University. His research focuses on creatively leveraging advanced virtual/augmented reality (VR/AR) and artificial intelligence (AI) techniques in healthcare and medicine applications and his achievements in relevant areas has been well recognized by the academic community. He won the Hong Kong Medical and Health Device Industries Association Student Research Award for his PhD study on VR-based simulation systems for surgical training and planning. He won 5 best paper awards for his research on AI-driven medical image analysis and computer-assisted surgery. He served as a local organization chair for MICCAI 2019, program committee members for AAAI, IJCAI, MICCAI, etc., speakers for many conferences, seminars, and forums, and referees for many prestigious journals in relevant fields.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Dr. Xi Zheng
Director of Intelligent Systems Research Group
Macquarie University, Australia

Abstract:
Autonomous driving has shown great potential to reform modern transportation. Yet its reliability and safety have drawn a lot of attention and concerns. Compared with traditional software systems, autonomous driving systems (ADSs) often use deep neural networks in tandem with logic-based modules. This new paradigm poses unique challenges for software testing. Despite the recent development of new ADS testing techniques, it is not clear to what extent those techniques have addressed the needs of ADS practitioners. To fill this gap, we have published a few works and I will present some of them. The first work is to reduce and prioritize test for multi-module autonomous driving systems (Accepted in FSE’22). The second work is to conduct comprehensive study to identify the current practices, needs and gaps in testing autonomous driving systems (Accepted also in FSE’22). The third work is to analyse the robustness issues in the deep learning driving models (Accepted in PerCom’20). The fourth work is to generate test cases from traffic rules for autonomous driving models (Accepted in TSE’22). I will also cover some ongoing and future work in autonomous driving systems.

Biography:
Dr. Xi Zheng received the Ph.D. in Software Engineering from the University of Texas at Austin in 2015. From 2005 to 2012, he was the Chief Solution Architect for Menulog Australia. He is currently the Director of Intelligent Systems Research Group, Director of International engagement in the School of Computing, Senior Lecturer (aka Associate Professor US) and Deputy Program Leader in Software Engineering, Macquarie University, Australia. His research interests include Internet of Things, Intelligent Software Engineering, Machine Learning Security, Human-in-the-loop AI, and Edge Intelligence. He has secured more than $1.2 million competitive funding in Australian Research Council (Linkage and Discovery) and Data61 (CRP) projects on safety analysis, model testing and verification, and trustworthy AI on autonomous vehicles. He also won a few awards including Deakin Industry Researcher (2016) and MQ Earlier Career Researcher (Runner-up 2020). He has a number of highly cited papers and best conference papers. He serves as PC members for CORE A* conferences including FSE (2022) and PerCom (2017-2023). He also serves as the PC chairs of IEEE CPSCom-2021, IEEE Broadnets-2022 and associate editor for Distributed Ledger Technologies.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Dr. C. Mohan
Distinguished Visiting Professor, Tsinghua University

Abstract:
In this talk, I will first introduce traditional (non-cloud) parallel and distributed database systems. Concepts like SQL and NoSQL systems, data replication, distributed and parallel query processing, and data recovery after different types of failures will be covered. Then, I will discuss how the emergence of the (public) cloud has introduced new requirements on parallel and distributed database systems, and how such requirements have necessitated fundamental changes to the architectures of such systems. I will illustrate the related developments by discussing some of the details of systems like Alibaba POLARDB, Microsoft Azure SQL DB, Microsoft Socrates, Azure Synapse POLARIS, Google Spanner, Google F1, CockroachDB, Amazon Aurora, Snowflake and Google AlloyDB.

Biography:
Dr. C. Mohan is currently a Distinguished Visiting Professor at Tsinghua University in China, a Visiting Researcher at Google, a Member of the inaugural Board of Governors of Digital University Kerala, and an Advisor of the Kerala Blockchain Academy (KBA) and the Tamil Nadu e-Governance Agency (TNeGA) in India. He retired in June 2020 from being an IBM Fellow at the IBM Almaden Research Center in Silicon Valley. He joined IBM Research (San Jose, California) in 1981 where he worked until May 2006 on several topics in the areas of database, workflow, and transaction management. From June 2006, he worked as the IBM India Chief Scientist, based in Bangalore, with responsibilities that relate to serving as the executive technical leader of IBM India within and outside IBM. In February 2009, at the end of his India assignment, Mohan resumed his research activities at IBM Almaden. Mohan is the primary inventor of the well-known ARIES family of database recovery and concurrency control methods, and the industry-standard Presumed Abort commit protocol. He was named an IBM Fellow, IBM’s highest technical position, in 1997 for being recognized worldwide as a leading innovator in transaction management. In 2009, he was elected to the United States National Academy of Engineering (NAE) and the Indian National Academy of Engineering (INAE). He received the 1996 ACM SIGMOD Edgar F. Codd Innovations Award in recognition of his innovative contributions to the development and use of database systems. In 2002, he was named an ACM Fellow and an IEEE Fellow. At the 1999 International Conference on Very Large Data Bases (VLDB), he was honored with the 10 Year Best Paper Award for the widespread commercial, academic and research impact of his ARIES work, which has been extensively covered in textbooks and university courses. From IBM, Mohan received 2 Corporate and 8 Outstanding Innovation/Technical Achievement Awards. He is an inventor on 50 patents. He was named an IBM Master Inventor in 1997. Mohan worked very closely with numerous IBM product and research groups, and his research results are implemented in numerous IBM and non-IBM prototypes and products like DB2, MQSeries, WebSphere, Informix, Cloudscape, Lotus Notes, Microsoft SQLServer, Sybase and System Z Parallel Sysplex. During the last many years, he focused on Blockchain, AI, Big Data and Cloud technologies (https://bit.ly/sigBcP, https://bit.ly/CMoTalks, https://bit.ly/CMgMDS). Since 2017, he has been an evangelist of permissioned blockchains and the myth buster of permissionless blockchains. During 1H2021, Mohan was the Shaw Visiting Professor at the National University of Singapore (NUS) where he taught a seminar course on distributed data and computing. In 2019, he became an Honorary Advisor to TNeGA of Chennai for its blockchain and other projects. In 2020, he joined the Advisory Board of KBA of India.
Since 2016, he has been a Distinguished Visiting Professor of China’s prestigious Tsinghua University in Beijing. In 2021, he was inducted as a member of the inaugural Board of Governors of the new Indian university Digital University Kerala (DUK). Mohan launched his consulting career by becoming a Consultant to Microsoft’s Data Team in October 2020. In March 2022, he became a consultant at Google with the title of Visiting Researcher. He has been on the advisory board of IEEE Spectrum and has been an editor of VLDB Journal, and Distributed and Parallel Databases. In the past, he has been a member of the IBM Academy of Technology’s Leadership Team, IBM’s Research Management Council, IBM’s Technical Leadership Team, IBM India’s Senior Leadership Team, the Bharti Technical Advisory Council, the Academic Senate of the International Institute of Information Technology in Bangalore, and the Steering Council of IBM’s Software Group Architecture Board. Mohan received his PhD in computer science from the University of Texas at Austin in 1981. In 2003, he was named a Distinguished Alumnus of IIT Madras from which he received a B.Tech. in chemical engineering in 1977. Mohan is a frequent speaker in North America, Europe and Asia. He has given talks in 43 countries. He is highly active on social media and has a huge following. More information can be found in the Wikipedia page at https://bit.ly/CMwIkP and his homepage at https://bit.ly/CMoDUK.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Prof. Anupam Chattopadhyay
Associate Professor, NTU

Abstract:
The continued scaling of horizontal and vertical physical features of silicon-based complementary metal-oxide-semiconductor (CMOS) transistors, termed as “More Moore”, has a limited runway and would eventually be replaced with “Beyond CMOS” technologies. There has been a tremendous effort to follow Moore’s law but it is currently approaching atomistic and quantum mechanical physics boundaries. This has led to active research in other non-CMOS technologies such as memristive devices, carbon nanotube field-effect transistors, quantum computing, etc. Several of these technologies have been realized on practical devices with promising gains in yield, integration density, runtime performance, and energy efficiency. Their eventual adoption is largely reliant on the continued research of Electronic Design Automation (EDA) tools catering to these specific technologies. Indeed, some of these technologies present new challenges to the EDA research community, which are being addressed through a series of innovative tools and techniques. In this tutorial, we will particularly cover the two phases of EDA flow, logic synthesis, and technology mapping, for two types of emerging technologies, namely, in-memory computing and quantum computing.

Biography:
Anupam Chattopadhyay received his B.E. degree from Jadavpur University, India, MSc. from ALaRI, Switzerland, and Ph.D. from RWTH Aachen in 2000, 2002, and 2008 respectively. From 2008 to 2009, he worked as a Member of Consulting Staff in CoWare R&D, Noida, India. From 2010 to 2014, he led the MPSoC Architectures Research Group in RWTH Aachen, Germany as a Junior Professor. Since September 2014, Anupam was appointed as an Assistant Professor in SCSE, NTU, where he got promoted to Associate Professor with Tenure from August 2019. Anupam is an Associate Editor of IEEE Embedded Systems Letters and series editor of Springer Book Series on Computer Architecture and Design Methodologies. Anupam received Borcher’s plaque from RWTH Aachen, Germany for outstanding doctoral dissertation in 2008, nomination for the best IP award in the ACM/IEEE DATE Conference 2016 and nomination for the best paper award in the International Conference on VLSI Design 2018 and 2020. He is a fellow of Intercontinental Academia and a senior member of IEEE and ACM.

Enquiries: Mr Jeff Liu at Tel. 3943 0624

Speaker:
Professor Peter J. Stuckey
Professor, Department of Data Science and Artificial Intelligence
Monash University

Abstract:
Decision tree learning is a widely used approach in machine learning, favoured in applications that require concise and interpretable models. Heuristic methods are traditionally used to quickly produce models with reasonably high accuracy. A commonly criticised point, however, is that the resulting trees may not necessarily be the best representation of the data in terms of accuracy and size. In recent years, this motivated the development of optimal classification tree algorithms that globally optimise the decision tree in contrast to heuristic methods that perform a sequence of locally optimal decisions.
In this talk I will explore the history of building decision trees, from greedy heuristic methods to modern optimal approaches.
In particular I will discuss a novel algorithm for learning optimal classification trees based on dynamic programming and search. Our algorithm supports constraints on the depth of the tree and number of nodes. The success of our approach is attributed to a series of specialised techniques that exploit properties unique to classification trees. Whereas algorithms for optimal classification trees have traditionally been plagued by high runtimes and limited scalability, we show in a detailed experimental study that our approach uses only a fraction of the time required by the state-of-the-art and can handle datasets with tens of thousands of instances, providing several orders of magnitude improvements and notably contributing towards the practical realisation of optimal decision trees.

Biography:
Professor Peter J. Stuckey is a Professor in the Department of Data Science and Artificial Intelligence in the Faculty of Information Technology at Monash University. Peter Stuckey is a pioneer in constraint programming and logic programming. His research interests include: discrete optimization; programming languages, in particular declarative programing languages; constraint solving algorithms; path finding; bioinformatics; and constraint-based graphics; all relying on his expertise in symbolic and constraint reasoning. He enjoys problem solving in any area, having publications in e.g. databases, election science, system security, and timetabling, and working with companies such as Oracle and Rio Tinto on problems that interest them.

Peter Stuckey received a B.Sc and Ph.D both in Computer Science from Monash University in 1985 and 1988 respectively. Since then he has worked at IBM T.J. Watson Research Labs, the University of Melbourne and Monash University. In 2009 he was recognized as an ACM Distinguished Scientist. In 2010 he was awarded the Google Australia Eureka Prize for Innovation in Computer Science for his work on lazy clause generation. He was awarded the 2010 University of Melbourne Woodward Medal for most outstanding publication in Science and Technology across the university. In 2019 he was elected as an AAAI Fellow. and awarded the Association of Constraint Programming Award for Research Excellence. He has over 125 journal and 325 conference publications and 17,000 citations with an h-index of 62.

Enquiries: Mr. Jeff Liu at Tel. 3943 0624

Speaker:
Prof. CAI Shaowei
Institute of Software
Chinese Academy of Sciences

Abstract:
Satisfiability Modulo Theories (SMT) is the problem of deciding the satisfiability of a first order logic formula with respect to certain background theories. SMT solvers have become important formal verification engines, with applications in various domains. In this talk, I will introduce the basis of SMT solving and present our work on improving a famous SMT solver Z3, leading to Z3++, which has won 2 Gold Medals out of 6 from SMT Competition 2022.

Biography:
Shaowei Cai is a professor in Institute of Software, Chinese Academy of Sciences. He has obtained his PhD from Peking University in 2012, with Doctoral Dissertation Award. His research focus on constraint solving (particularly SAT, SMT, and integer programming), combinatorial optimization, and formal verification, as well as their applications in industries. He has won more than 10 Gold Medals from SAT and SMT Competitions, and the Best Paper Award of SAT 2021 conference.

Join Zoom Meeting:
https://cuhk.zoom.us/j/99411951727

Enquiries: Ms. Karen Chan at Tel. 3943 8439

Speaker:
Prof. Hai Zhou
Associate Professor, Department of Electrical and Computer Engineering
Northwestern University

Abstract:
With the increasing cost and complexity in semiconductor hardware designs, circuit IP protection has become an important and challenging problem in hardware security. Logic encryption is a promising technique that modifies a sensitive circuit to a locked one with a password, such that only authorized users can access it. During its history of more than 20 years, many different attacks and defenses have been designed and proposed. In this talk, after a brief introduction to logic encryption, I will present important attacking and defending techniques in the field. Especially, the focus will be on the few key attacks and defenses created in NuLogiCS group at Northwestern.

Biography:
Hai Zhou is the director of the NuLogiCS Research Group in the Electrical and Computer Engineering at Northwestern University and a member of the Center for Ultra Scale Computing and Information Security (CUCIS). His research interest is on Logical Methods for Computer Systems (LogiCS), where logics is used to construct reactive computer systems (in the form of hardware, software, or protocol) and to verify their properties (e.g. correctness, security, and efficiency). In other words, he is interested in algorithms, formal methods, optimization, and their applications to security, machine learning, and economics.

Enquiries: Ms. Karen Chan at Tel. 3943 8439

Speaker:
Dr. Baoyuan WU
Associate Professor, School of Data Science
The Chinese University of Hong Kong, Shenzhen

Abstract:
In this talk, Dr. Wu will review the development of backdoor learning and his lastest works on backdoor attack and defense. The first is the backdoor attack with sample-specific triggers, which can bypass most existing defense methods, as they are mainly developed for defending against sample-agnostic triggers. Then, he will introduce two effective backdoor defense methods which could preclude the backdoor injection during the training process, through exploring some intrinsic properties of poisoned samples. Finally, he will introduce BackdoorBench, which is a comprehensive benchmark containing mainstream backdoor attack and defense methods, as well as 8,000 pairs of attack-defense evaluations, several interesting findings and analysis. It was recently released at “What is BackdoorBench? ”

Biography:
Dr. Baoyuan Wu is an Associate Professor of School of Data Science, the Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), and the director of the Secure Computing Lab of Big Data, Shenzhen Research Institute of Big Data (SRIBD). His research interests are AI security and privacy, machine learning, computer vision and optimization. He has published 50+ top-tier conference and journal papers, including TPAMI, IJCV, NeurIPS, CVPR, ICCV, ECCV, ICLR, AAAI. He is currently serving as an Associate Editor of Neurocomputing, Area Chair of NeurIPS 2022, ICLR 2022/2023, AAAI 2022.

Join Zoom Meeting:
https://cuhk.zoom.us/j/91408751707

Enquiries: Ms. Karen Chan at Tel. 3943 8439

Speaker:
Dr. Li Zhenguo
Director, AI Theory Lab
Huawei Noah’s Ark Lab, Hong Kong

Abstract:
Noah’s Ark Lab is the AI research center for Huawei, with the mission of making significant contribution to both the company and society through innovation in artificial intelligence (AI), data mining and related fields. Our AI theory team focuses on the fundamental research in machine learning, including cutting-edge theories and algorithms such as out-of-distribution (OoD) generalization and controllable generative modeling, and disruptive applications such as self-driving. In this talk, we will present some of our progresses in out-of-distribution generalization, including OoD-learnable theories and model selection, understanding and quantification of OoD properties of various benchmark datasets, and related applications. We will also highlight some key challenges for future studies.

Biography:
Zhenguo Li is currently the director of the AI Theory Lab in Huawei Noah’s Ark Lab, Hong Kong. Before joining Huawei Noah’s Ark lab, he was an associate research scientist in the department of electrical engineering, Columbia University, working with Prof. Shih-Fu Chang. He received BS and MS degrees in mathematics at Peking University, and PhD degree in machine learning at The Chinese University of Hong Kong, advised by Prof. Xiaoou Tang. His current research interests include machine learning and its applications.

Enquiries: Ms. Karen Chan at Tel. 3943 8439

Speaker:
Prof. Au, Kwok Wai Samuel
Professor, Department of Mechanical and Automation Engineering, CUHK
Professor, Department of Surgery, CUHK
Co-Director, Chow Yuk Ho Technology Centre for Innovative Medicine, CUHK
Director, Multiscale Medical Robotic Center, InnoHK

Abstract:
Over the past decades, a wide range of bio-inspired legged robots have been developed that can run, jump, and climb over a variety of challenging surfaces. However, in terms of maneuverability they still lag far behind animals. Animals can effectively use their mechanical body and external appendages (such as tails) to achieve spectacular maneuverability, energy efficient locomotion, and robust stabilization to large perturbations which may not be easily attained in the existing legged robots. In this talk, we will present our efforts on the development of innovative legged robots with greater mobility/efficiency/robustness, comparable to its biological counterpart. We will discuss the fundamental challenges in legged robots and demonstrate the feasibility of developing such kinds of agile systems. We believe our solutions could potentially lead to more efficient legged robot design and give the legged robot animal-like mobility and robustness. Furthermore, we will also present our robotic development on surgery domain and show how these technologies can be integrated with legged robots to create novel teleoperated legged mobile manipulators for service and construction applications.

Biography:
Dr. Kwok Wai Samuel Au is currently a Professor of the Department of Mechanical and Automation Engineering and Department of Surgery (by courtesy) at CUHK, and the Founding Director of Multiscale Medical Robotics Center, InnoHK. In Sept 2019, Dr. Au found Cornerstone Robotics and has been serving as the president of the company, aiming to create affordable surgical robotic solution. Dr. Au received the B.Eng. and M.Phil degrees in Mechanical and Automation Engineering from CUHK in 1997 and 1999, respectively and completed his Ph.D. degree in Mechanical Engineering at MIT in 2007. During his PhD study, Prof. Hugh Herr, Dr. Au, and other colleagues from MIT Biomechatronics group co-invented the MIT Powered Ankle-foot Prosthesis.

Before joining CUHK(2016), he was the manager of Systems Analysis of the New Product Development Department at Intuitive Surgical, Inc. At Intuitive Surgical, he co-invented and was leading the software and control algorithm development for the FDA cleared da Vinci Si Single-Site surgical platform (2012), Single-Site Wristed Needle Driver (2014), and da Vinci Xi Single-Site surgical platform (2016). He was also a founding team member for the early development of Intuitive Surgical’s FDA cleared robot-assisted catheter system, da Vinci ION system from 2008 to 2012.

Dr. Au co-authored over 60 peer-reviewed manuscripts and conference journals, 17 granted US patents/EP, and 3 pending US Patents. He has won numerous awards including the first prize in the American Society of Mechanical Engineers (ASME) Student Mechanism Design Competition in 2007, Intuitive Surgical Problem Solving Award in 2010, and Intuitive Surgical Inventor Award in 2011.

Enquiries: Ms. Karen Chan at Tel. 3943 8439