Generating Robust Counterfactual Witnesses for Graph Neural Networks

arXiv:2404.19519v1 Announce Type: new
Abstract: This paper introduces a new class of explanation structures, called robust counterfactual witnesses (RCWs), to provide robust, both counterfactual and factual explanations for graph neural networks. Given a graph neural network M, a robust counterfactual witness refers to the fraction of a graph G that are counterfactual and factual explanation of the results of M over G, but also remains so for any "disturbed" G by flipping up to k of its node pairs. We …

abstract arxiv class counterfactual cs.db cs.lg graph graph neural network graph neural networks network networks neural network neural networks paper robust type witness