Skip to content

Queimo/sgnn_lrp_via_mp

 
 

Repository files navigation

Efficient Computation of Higher-Order Subgraph Attribution via Message Passing

This is the repository of the paper "Efficient Computation of Higher-Order Subgraph Attribution via Message Passing" accepted by ICML 2022. The full paper is available on (tbd).

  • The experiments of runtime comparison on five datasets are in the notebook experiments.ipynb.
  • The experiments of Accuracy/AUROC on BA-2motif benchmark and the model activation/pruning task on MUTAG and Graph-SST2 are in the notebook experiments.ipynb.
  • The comparison experiment with baselines is in the notebook baseline_comparison.ipynb.
  • To train the model by yourself please refer to the notebook train+lrp_validation.ipynb.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 78.2%
  • Python 21.8%