Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Semi-Supervised Graph Classification: A Hierar...

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.

izuna385

May 28, 2019
Tweet

More Decks by izuna385

Other Decks in Technology

Transcript

  1. • input each graph instance: g labeled graph set and

    unlabeled graph set graph instance adjacency matrix
  2. • 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
  3. • Task Collect Class Prediction for unlabeled • Loss function

    labeled graph instances unlabeled graph instances
  4. • Supervised Loss (for labeled graphs ) • Disagreement Loss(for

    unlabeled graphs ) Disagreement means IC and HC prediction mismatch.
  5. Active Iteration Disagreement means IC and HC prediction mismatch. Ask

    annotator for annotating class of graphs which HC and IC have top-disagreement with.