圖神經網路之推薦系統與關係推估
Graph Neural Networks for Recommendation and Relation Estimation
| 節 | 週三 |
|---|---|
2 09:00–09:50 | 圖神經網路之推薦系統與關係推估 M-b01 3 節連堂 |
3 10:10–11:00 | |
4 11:10–12:00 |
* 根據陽明交大上課時間表所列
Some complicated data involving relationships can be represented as a graph that consists of nodes and edges between nodes. Such graphs can serve as a fundamental tool for modeling social, technological, and biological systems. This course focuses on the computational, algorithmic, and modeling challenges specific to the analysis of massive graphs. By means of studying the underlying graph structure and its features, students are introduced to machine learning techniques and data mining tools that can help us to reveal insights into a variety of networks. We will focus on representation learning and Graph Neural Networks. Furthermore, we will cover algorithms for the World Wide Web, influence maximization, disease outbreak detection, and social network analysis.
Computer Programming, Probability (Statistics (I) in our Management College is sufficient), Linear Algebra
TA: 馮景泰 hinatataro.mg14 AT nycu.edu.tw Reference site: https://snap.stanford.edu/class/cs224w-2020/ The course content will be adjusted based on the teaching situation and unforeseen circumstances, and the planned schedule may be modified accordingly. Students are expected to uphold intellectual property rights and refrain from using illegally photocopied textbooks.
30% 3 labs (3 Colabs plus Colab 0(to familiarize you with the setup; no hand-in required)). 20% two homeworks 30% final exam or a novel research improvement 20% paper presentation or your novel research improvement presentation
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction; Machine Learning for Graphs |
| 第 2 週 | Machine Learning for Graphs |
| 第 3 週 | Traditional Methods for ML on Graphs |
| 第 4 週 | Node Embeddings |
| 第 5 週 | Link Analysis: PageRank |
| 第 6 週 | Label Propagation for Node Classification |
| 第 7 週 | Graph Neural Networks 1: GNN Model |
| 第 8 週 | Graph Neural Networks 1: GNN Model |
| 第 9 週 | Theory Day and CMCT |
| 第 10 週 | Graph Neural Networks 2: Design Space |
| 第 11 週 | Novel Research Improvement Proposal Check-Up Paper Presentation selection Physical course follows |
| 第 12 週 | Applications of Graph Neural Networks |
| 第 13 週 | Theory of Graph Neural Networks |
| 第 14 週 | Knowledge Graph Embeddings |
| 第 15 週 | Final Exam |
| 第 16 週 | Final Presentation |
Notes and reading assignments will be posted Optional Reading: Graph Representation Learning by William L. Hamilton Networks, Crowds, and Markets: Reasoning About a Highly Connected World by David Easley and Jon Kleinberg Network Science by Albert-László Barabási
- 地點
- Make an appointment by email
- 時間
- Make an appointment by email
- 聯絡方式
- shih-yu.tsai AT nycu.edu.tw