Robust Counterfactual Explanations on Graph Neural Networks

Mohit Bajaj, Lingyang Chu, Zi Yu Xue, Jian Pei, Lanjun Wang, Peter Cho-Ho Lam, Yong Zhang

Keywords: Counterfactual, explanations, GNN, robust, graph neural networks, interpretation, explainable AI, decision logic

TL;DR: We propose a novel method to produce robust counterfactual explanations for the predictions of Graph Neural Networks.

Abstract: Massive deployment of Graph Neural Networks (GNNs) in high-stake applications generates a strong demand for explanations that are robust to noise and align well with human intuition. Most existing methods generate explanations by identifying a subgraph of an input graph that has a strong correlation with the prediction. These explanations are not robust to noise because independently optimizing the correlation for a single input can easily overfit noise. Moreover, they are not counterfactual because removing an identified subgraph from an input graph does not necessarily change the prediction result. In this paper, we propose a novel method to generate robust counterfactual explanations on GNNs by explicitly modelling the common decision logic of GNNs on similar input graphs. Our explanations are naturally robust to noise because they are produced from the common decision boundaries of a GNN that govern the predictions of many similar input graphs. The explanations are also counterfactual because removing the set of edges identified by an explanation from the input graph changes the prediction significantly. Exhaustive experiments on many public datasets demonstrate the superior performance of our method.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://marketplace.huaweicloud.com/markets/aihub/notebook/detail/?id=e41f63d3-e346-4891-bf6a-40e64b4a3278

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2107.04086/code)