Semi-Supervised Graph Classification: A Hierarchical Graph Perspective(WWW19)

This slide is for supplement of reading paper, so it doesn't hold presentation-slide style, sorry.

1. 1 (Supplement slides for reading paper) Semi-Supervised Graph Classification: A Hierarchical Graph Perspective(WWW19) izunan385
2. Li, Jia, et al. "Semi-Supervised Graph Classification: A Hierarchical Graph Perspective." (2019).
3. • Task Collect Class Prediction for unlabeled
4. • input each graph instance: g labeled graph set and unlabeled graph set graph instance adjacency matrix
5. • output IC(graph Instance Classifier) receives graph info and outputs
   instance representation matrix
   predicted class probability vector HC(Hierarchical Graph Classifier) receives
   all graph instance( ) representation from IC
   graph-graph adjacency matrix and outputs predicted class prob matrix for all
6. • Task Collect Class Prediction for unlabeled • Loss function labeled graph instances unlabeled graph instances
7. • Supervised Loss (for labeled graphs ) • Disagreement Loss(for unlabeled graphs ) Disagreement means IC and HC prediction mismatch.
9. GCN W0: learnable parameter
10. GCN with self loop W0: learnable parameter
11. GCN(summarized) 0 https://www.experoinc.com/post/node-classification-by-graph-con network Adjacent/co-occurrence matrix has structure information. Propagation rule is learned during training.
12. https://docs.dgl.ai/tutorials/models/1_gnn/9_gat.html
13. Cautious Iteration
14. Cautious Iteration Here, sampling top confident prediction for each step
15. Active Iteration Disagreement means IC and HC prediction mismatch. Ask annotator for annotating class of graphs which HC and IC have top-disagreement with.