COMRECGC: Global Graph Counterfactual Explainer through Common Recourse
This addresses the need for interpretable GNNs in domains like drug discovery or computational biology, though it is incremental as it extends counterfactual explanation methods to a global, common recourse setting.
The paper tackles the problem of generating global counterfactual explanations for graph neural networks (GNNs) by introducing a method to find common recourse explanations, which transform 'reject' graphs into 'accept' graphs using a small set of recourses. It demonstrates superior performance against baselines on four real-world datasets, showing that common recourse explanations are comparable or superior to existing graph counterfactual methods.
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.