Heterogeneous Graph Representation Learning and Applications
暫譯: 異質圖表示學習與應用

1. Introduction

1.1 Basic concepts and definitions

1.2 Graph representation

1.3 Heterogeneous graph representation and challenges

1.4 Organization of the book

2. The State-of-the-art of Heterogeneous Graph Representation

2.1 Method taxonomy

2.1.1 Structure-preserved representation

2.1.2 Attribute-assisted representation

2.1.3 Dynamic representation

2.1.4 Application-oriented representation

2.2 Technique summary

2.2.1 Shallow model

2.2.2 Deep model

2.3 Open sources

Part One: Techniques

3. Structure-preserved Heterogeneous Graph Representation

3.1 Meta-path based random walk

3.2 Meta-path based decomposition

3.3 Relation structure awareness

3.4 Network schema preservation

4. Attribute-assisted Heterogeneous Graph Representation

4.1 Heterogeneous graph attention network

4.2 Heterogeneous graph structure learning

5. Dynamic Heterogeneous Graph Representation

5.1 Incremental Learning

5.2 Temporal Interaction

5.3 Sequence Information

6. Supplementary of Heterogeneous Graph Representation

6.1 Adversarial Learning

6.2 Importance Sampling

6.3 Hyperbolic Representation

Part Two: Applications

7. Heterogeneous Graph Representation for Recommendation

7.1 Top-N Recommendation

7.2 Cold-start Recommendation

7.3 Author Set Recommendation

8. Heterogeneous Graph Representation for Text Mining

8.1 Short Text Classification

8.2 News Recommendation with Preference Disentanglement

8.3 News recommendation with long/short-term interest modeling

9. Heterogeneous Graph Representation for Industry Application

9.1 Cash-out User Detection

9.2 Intent Recommendation

9.3 Share Recommendation

9.4 Friend-Enhanced Recommendation

10. Future Research Directions

11. Conclusion