Graph Counterfactual Explainable AI via Latent Space Traversal

TL;DR

This paper introduces a novel method for generating counterfactual explanations for graph neural networks by traversing a latent space in a permutation-equivariant autoencoder, enabling continuous and robust explanations.

Contribution

It proposes a permutation-equivariant graph variational autoencoder to produce continuous counterfactual explanations for any differentiable graph classifier.

Findings

High-performing counterfactual explanations on three datasets

More robust than baseline methods

Seamless integration of discrete and continuous graph features

Abstract

Explaining the predictions of a deep neural network is a nontrivial task, yet high-quality explanations for predictions are often a prerequisite for practitioners to trust these models. Counterfactual explanations aim to explain predictions by finding the ''nearest'' in-distribution alternative input whose prediction changes in a pre-specified way. However, it remains an open question how to define this nearest alternative input, whose solution depends on both the domain (e.g. images, graphs, tabular data, etc.) and the specific application considered. For graphs, this problem is complicated i) by their discrete nature, as opposed to the continuous nature of state-of-the-art graph classifiers; and ii) by the node permutation group acting on the graphs. We propose a method to generate counterfactual explanations for any differentiable black-box graph classifier, utilizing a case-specific permutation equivariant graph variational autoencoder. We generate counterfactual explanations in a continuous fashion by traversing the latent space of the autoencoder across the classification boundary of the classifier, allowing for seamless integration of discrete graph structure and continuous graph attributes. We empirically validate the approach on three graph datasets, showing that our model is consistently high-performing and more robust than the baselines.