GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules

Burouj Armgaan, Manthan Dalmia, Sourav Medya, Sayan Ranu

Keywords: Graph Neural Network, Explainability, Global Factual Explanation, Symbolic Regression, Computation Trees

TL;DR: We generate formula based global explainations of graph neural networks using symbolic regression over computation trees identified through Shapley values.

Abstract: Instance-level explanation of graph neural networks (GNNs) is a well-studied area. These explainers, however, only explain an instance (e.g., a graph) and fail to uncover the combinatorial reasoning learned by a GNN from the training data towards making its predictions. In this work, we introduce GraphTrail, the first end-to-end, global, post-hoc GNN explainer that translates the functioning of a black-box GNN model to a boolean formula over the (sub)graph level concepts without relying on local explainers. GraphTrail is unique in automatically mining the discriminative subgraph-level concepts using Shapley values. Subsequently, the GNN predictions are mapped to a human-interpretable boolean formula over these concepts through symbolic regression. Extensive experiments across diverse datasets and GNN architectures demonstrate significant improvement over existing global explainers in mapping GNN predictions to faithful logical formulae. The robust and accurate performance of GraphTrail makes it invaluable for improving GNNs and facilitates adoption in domains with strict transparency requirements.

Primary Area: Graph neural networks

Submission Number: 12856