MetaGMT: Improving Actionable Interpretability of Graph Multilinear Networks via Meta-Learning Filtration
This work addresses the need for trustworthy GNNs in high-stakes domains like healthcare and finance by enhancing actionable interpretability, though it is incremental as it builds on existing Graph Multi-linear Networks.
The paper tackles the problem of unreliable explanations in inherently interpretable Graph Neural Networks (GNNs) by proposing MetaGMT, a meta-learning framework that improves explanation fidelity and robustness to spurious correlations, achieving up to an 8% increase in Explanation ROC on benchmarks.
The growing adoption of Graph Neural Networks (GNNs) in high-stakes domains like healthcare and finance demands reliable explanations of their decision-making processes. While inherently interpretable GNN architectures like Graph Multi-linear Networks (GMT) have emerged, they remain vulnerable to generating explanations based on spurious correlations, potentially undermining trust in critical applications. We present MetaGMT, a meta-learning framework that enhances explanation fidelity through a novel bi-level optimization approach. We demonstrate that MetaGMT significantly improves both explanation quality (AUC-ROC, Precision@K) and robustness to spurious patterns, across BA-2Motifs, MUTAG, and SP-Motif benchmarks. Our approach maintains competitive classification accuracy while producing more faithful explanations (with an increase up to 8% of Explanation ROC on SP-Motif 0.5) compared to baseline methods. These advancements in interpretability could enable safer deployment of GNNs in sensitive domains by (1) facilitating model debugging through more reliable explanations, (2) supporting targeted retraining when biases are identified, and (3) enabling meaningful human oversight. By addressing the critical challenge of explanation reliability, our work contributes to building more trustworthy and actionable GNN systems for real-world applications.