SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.02780 · 2023

Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The success of graph neural networks (GNNs) provokes the question about explainability: ``Which fraction of the input graph is the most determinant of the prediction?'' Particularly, parametric explainers prevail in existing approaches because of their more robust capability to decipher the black-box (i.e., target GNNs). In this paper, based on the observation that graphs typically share some common motif patterns, we propose a novel non-parametric subgraph matching framework, dubbed MatchExplainer, to explore explanatory subgraphs. It couples the target graph with other counterpart instances and identifies the most crucial joint substructure by minimizing the node corresponding-based distance. Moreover, we note that present graph sampling or node-dropping methods usually suffer from the false positive sampling problem. To alleviate this issue, we designed a new augmentation paradigm named MatchDrop. It takes advantage of MatchExplainer to fix the most informative portion of the graph and merely operates graph augmentations on the rest less informative part. Extensive experiments on synthetic and real-world datasets show the effectiveness of our MatchExplainer by outperforming all state-of-the-art parametric baselines with significant margins. Results also demonstrate that MatchDrop is a general scheme to be equipped with GNNs for enhanced performance. The code is available at: https://github.com/smiles724/MatchExplainer.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.02780")
get_code_for_paper("2301.02780")
have("2301.02780")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2301.02780.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2301.02780.svg)](https://syntology.ai/paper/2301.02780)

Connect an agent — have() is free.