MEGAN: Multi-Explanation Graph Attention Network

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.

24 pages, accepted for xAI 2023 conference portugal

References in corpus (10)

• Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning
• Scientific intuition inspired by machine learning generated hypotheses
• Implementing graph neural networks with TensorFlow-Keras
• GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation
• GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks
• Learning to Scaffold: Optimizing Model Explanations for Teaching
• Supervising Model Attention with Human Explanations for Robust Natural Language Inference
• DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees
• Encoding Concepts in Graph Neural Networks
• PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks