MEGAN: Multi-Explanation Graph Attention Network
This work addresses the need for improved interpretability in graph neural networks, particularly for regression tasks, by enabling multi-channel explanations, though it is incremental in extending attention-based methods.
The authors tackled the problem of generating multiple attributional explanations for graph regression predictions by proposing MEGAN, which outperformed existing methods in explanation accuracy and produced sparse, human-intuitive explanations on real-world datasets.
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.