AAAI2021 291页教程: ​Graph Neural Networks: Models and Applications

Graph Neural Networks: Models and Applications

Time and Location

Time: 15:00 pm - 18:00 pm, EST, Wednsday, February 3, 2021

Abstract

Graph structured data such as social networks and molecular graphs are ubiquitous in the real world. It is of great research importance to design advanced algorithms for representation learning on graph structured data so that downstream tasks can be facilitated. Graph Neural Networks (GNNs), which generalize the deep neural network models to graph structured data, pave a new way to effectively learn representations for graph-structured data either from the node level or the graph level. Thanks to their strong representation learning capability, GNNs have gained practical significance in various applications ranging from recommendation, natural language processing to healthcare. It has become a hot research topic and attracted increasing attention from the machine learning and data mining community recently. This tutorial of GNNs is timely for AAAI 2020 and covers relevant and interesting topics, including representation learning on graph structured data using GNNs, the robustness of GNNs, the scalability of GNNs and applications based on GNNs.

Tutorial Syllabus

1. Introduction
   1. Graphs and Graph Structured Data
   2. Tasks on Graph Structured Data
   3. Graph neural networks
2. Foundations
   1. Basic Graph Theory
   2. Graph Fourier Transform
3. Models
   1. Spectral-based GNN layers
   2. Spatial-based GNN layers
   3. Pooling Schemes for Graph-level Representation Learning
   4. Attacks and Robustness of Graph Neural Networks
   5. Deeper Graph Neural Networks
   6. Scalable Learning For Graph Neural Networks
   7. Self-supervised Learing for Graph Neural Networks
4. Applications
   1. Recommendation

Slides and Video

Image of Yao

Link: http://cse.msu.edu/~mayao4/tutorials/aaai2021/