| Course code | CSCI5650 |
| Course title | Graph Neural Networks 圖神經網絡 |
| Course description | Graph is a fundamental data structure with a wide range of applications. This course covers advanced topics in graph neural networks (GNN) that include, but are not limited to: introductory algorithms and analyses for graph mining, graph-based semi-supervised learning, graph embedding techniques, graph convolution networks, graph attention networks, graph encoder-decoder, graph transformer, knowledge graphs and translation models, application of graph algorithms, etc. 圖是具有廣泛應用程序的基本數據結構。 本科涵蓋圖神經網絡（GNN）的高級主題，包括但不限於：圖挖掘的入門算法和分析，基於圖的半監督學習，圖嵌入技術，圖卷積網絡，圖注意力網絡，圖 編碼器-解碼器，圖形轉換器，知識圖和轉換模型，圖算法的應用等。 |
| Unit(s) | 3 |
| Course level | Postgraduate |
| Semester | 1 or 2 |
| Grading basis | Graded |
| Grade Descriptors | A/A-: EXCELLENT – exceptionally good performance and far exceeding expectation in all or most of the course learning outcomes; demonstration of superior understanding of the subject matter, the ability to analyze problems and apply extensive knowledge, and skillful use of concepts and materials to derive proper solutions. B+/B/B-: GOOD – good performance in all course learning outcomes and exceeding expectation in some of them; demonstration of good understanding of the subject matter and the ability to use proper concepts and materials to solve most of the problems encountered. C+/C/C-: FAIR – adequate performance and meeting expectation in all course learning outcomes; demonstration of adequate understanding of the subject matter and the ability to solve simple problems. D+/D: MARGINAL – performance barely meets the expectation in the essential course learning outcomes; demonstration of partial understanding of the subject matter and the ability to solve simple problems. F: FAILURE – performance does not meet the expectation in the essential course learning outcomes; demonstration of serious deficiencies and the need to retake the course. |
| Learning outcomes | At the end of the course of studies, students will have acquired the ability to 1. Understand and be knowledgeable about the basic models and algorithms for graph mining and graph neural networks 2. Implement and evaluate some of the graph neural network models and algorithms presented in the course 3. Use the learned knowledge and applied them in a project that solves a real-world problem 4. Communicate concisely and clearly about how to use graph neural networks in solving a real-world problem |
| Assessment (for reference only) |
Examination: 30% Project: 30% Presentation: 20% Homework or assignment: 20% |
| Recommended Reading List | 1. Graph Mining: Laws, Tools, and Case Studies, Deepayan Chakrabarti and Christos Faloutsos, Morgan & Claypool Publishers; 1st Edition (October 19, 2012) 2. Mining Graph Data, Diane J. Cook and Lawrence B. Holder, John Wiley & Sons, 2006 3. Introduction to Graph Neural Networks, Zhiyuan Liu and Jie Zhou, Morgan & Claypool (March 20, 2020) |
| CSCIN programme learning outcomes | Course mapping |
| Upon completion of their studies, students will be able to: | |
| 1. identify, formulate, and solve computer science problems (K/S); | Y |
| 2. design, implement, test, and evaluate a computer system, component, or algorithm to meet desired needs (K/S); |
Y |
| 3. receive the broad education necessary to understand the impact of computer science solutions in a global and societal context (K/V); | |
| 4. communicate effectively (S/V); |
Y |
| 5. succeed in research or industry related to computer science (K/S/V); |
Y |
| 6. have solid knowledge in computer science and engineering, including programming and languages, algorithms, theory, databases, etc. (K/S); | Y |
| 7. integrate well into and contribute to the local society and the global community related to computer science (K/S/V); | |
| 8. practise high standard of professional ethics (V); | |
| 9. draw on and integrate knowledge from many related areas (K/S/V); |
Y |
| Remarks: K = Knowledge outcomes; S = Skills outcomes; V = Values and attitude outcomes; T = Teach; P = Practice; M = Measured | |