Global Concept Explanations for Graphs by Contrastive Learning

TL;DR

This paper introduces a contrastive learning-based method to extract global concept explanations from graph neural networks, aiding scientific understanding and model interpretability in graph property prediction tasks.

Contribution

The authors propose a novel approach to identify global concepts in graph neural networks using dense clusters in a self-explaining latent space, enhanced by prototype graphs and GPT-4 hypotheses.

Findings

Correctly reproduces structural rules in synthetic tasks

Rediscovers established rules in real-world molecular property tasks

Provides more detailed structural explanations than existing methods

Abstract

Beyond improving trust and validating model fairness, xAI practices also have the potential to recover valuable scientific insights in application domains where little to no prior human intuition exists. To that end, we propose a method to extract global concept explanations from the predictions of graph neural networks to develop a deeper understanding of the tasks underlying structure-property relationships. We identify concept explanations as dense clusters in the self-explaining Megan models subgraph latent space. For each concept, we optimize a representative prototype graph and optionally use GPT-4 to provide hypotheses about why each structure has a certain effect on the prediction. We conduct computational experiments on synthetic and real-world graph property prediction tasks. For the synthetic tasks we find that our method correctly reproduces the structural rules by which they were created. For real-world molecular property regression and classification tasks, we find that our method rediscovers established rules of thumb. More specifically, our results for molecular mutagenicity prediction indicate more fine-grained resolution of structural details than existing explainability methods, consistent with previous results from chemistry literature. Overall, our results show promising capability to extract the underlying structure-property relationships for complex graph property prediction tasks.