MEGAN: Multi-Explanation Graph Attention Network

TL;DR

MEGAN introduces a multi-channel, attention-based graph neural network that provides interpretable, explanation-supervised node and edge attributions, improving explainability and fidelity in graph regression tasks.

Contribution

It is the first to produce multi-channel explanations independent of task specifics, enhancing interpretability and allowing active training of explanations.

Findings

Outperforms baseline explainability methods on synthetic data.

Achieves near-perfect explanation accuracy during supervision.

Produces sparse, high-fidelity explanations aligned with human intuition.

Abstract

We propose a multi-explanation graph attention network (MEGAN). Unlike existing graph explainability methods, our network can produce node and edge attributional explanations along multiple channels, the number of which is independent of task specifications. This proves crucial to improve the interpretability of graph regression predictions, as explanations can be split into positive and negative evidence w.r.t to a reference value. Additionally, our attention-based network is fully differentiable and explanations can actively be trained in an explanation-supervised manner. We first validate our model on a synthetic graph regression dataset with known ground-truth explanations. Our network outperforms existing baseline explainability methods for the single- as well as the multi-explanation case, achieving near-perfect explanation accuracy during explanation supervision. Finally, we demonstrate our model's capabilities on multiple real-world datasets. We find that our model produces sparse high-fidelity explanations consistent with human intuition about those tasks.