COMRECGC: Global Graph Counterfactual Explainer through Common Recourse

TL;DR

This paper introduces COMRECGC, a novel algorithm for generating common recourse explanations in graph neural networks, providing a global counterfactual explanation method that outperforms baselines on real-world datasets.

Contribution

The paper formalizes the common recourse explanation problem for GNNs and proposes an effective algorithm, COMRECGC, for generating global counterfactual explanations.

Findings

COMRECGC outperforms strong baselines on four datasets.

Common recourse explanations are comparable or superior to individual counterfactuals.

The method is applicable to real-world applications like drug discovery.

Abstract

Graph neural networks (GNNs) have been widely used in various domains such as social networks, molecular biology, or recommendation systems. Concurrently, different explanations methods of GNNs have arisen to complement its black-box nature. Explanations of the GNNs' predictions can be categorized into two types--factual and counterfactual. Given a GNN trained on binary classification into ''accept'' and ''reject'' classes, a global counterfactual explanation consists in generating a small set of ''accept'' graphs relevant to all of the input ''reject'' graphs. The transformation of a ''reject'' graph into an ''accept'' graph is called a recourse. A common recourse explanation is a small set of recourse, from which every ''reject'' graph can be turned into an ''accept'' graph. Although local counterfactual explanations have been studied extensively, the problem of finding common recourse for global counterfactual explanation remains unexplored, particularly for GNNs. In this paper, we formalize the common recourse explanation problem, and design an effective algorithm, COMRECGC, to solve it. We benchmark our algorithm against strong baselines on four different real-world graphs datasets and demonstrate the superior performance of COMRECGC against the competitors. We also compare the common recourse explanations to the graph counterfactual explanation, showing that common recourse explanations are either comparable or superior, making them worth considering for applications such as drug discovery or computational biology.