Global Explainability of GNNs via Logic Combination of Learned Concepts
This addresses the need for interpretability and debugging in GNNs, offering a novel diagnostic tool for researchers and practitioners, though it is incremental in advancing global explainability methods.
The paper tackles the problem of providing global explanations for Graph Neural Networks (GNNs) by proposing GLGExplainer, which generates explanations as Boolean combinations of learned graphical concepts, achieving perfect alignment with ground-truth on synthetic data and matching domain knowledge on real-world data.
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 provides accurate and human-interpretable global explanations that are perfectly aligned with ground-truth explanations (on synthetic data) or match existing domain knowledge (on real-world data). Extracted formulas are faithful to the model predictions, to the point of providing insights into some occasionally incorrect rules learned by the model, making GLGExplainer a promising diagnostic tool for learned GNNs.