Global Explainability of GNNs via Logic Combination of Learned Concepts
Lists
Only you see this
Abstract
While instance-level explanation of GNN is a well-studied problem with plenty of approaches being developed, providing a global explanation for the behaviour of a GNN is much less explored, despite its potential in interpretability and debugging. Existing solutions either simply list local explanations for a given class, or generate a synthetic prototypical graph with maximal score for a given class, completely missing any combinatorial aspect that the GNN could have learned. In this work we propose GLGExplainer (Global Logic-based GNN Explainer), the first Global Explainer capable of generating explanations as arbitrary Boolean combinations of learned graphical concepts. GLGExplainer is a fully differentiable architecture that takes local explanations as inputs and combines them into a logic formula over graphical concepts, represented as clusters of local explanations. Contrary to existing solutions, GLGExplainer manages to provide accurate and human-interpretable global explanations in both synthetic and real world datasets.
BibTeX
@inproceedings{azzolin2023global,
author = {Steve Azzolin and Antonio Longa and Pietro Barbiero and Pietro Lio and Andrea Passerini},
title = {{Global Explainability of GNNs via Logic Combination of Learned Concepts}},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://openreview.net/forum?id=OTbRTIY4YS},
}