PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction
It addresses the problem of model transparency for researchers and practitioners in web applications like recommendation systems, though it is incremental as it extends existing GNN explanation methods to link prediction.
The paper tackles the lack of explanation methods for graph neural networks in link prediction tasks, proposing PaGE-Link, which generates path-based explanations that improve AUC for recommendation by 9-35% and are preferred by 78.79% of users in human evaluation.
Transparency and accountability have become major concerns for black-box machine learning (ML) models. Proper explanations for the model behavior increase model transparency and help researchers develop more accountable models. Graph neural networks (GNN) have recently shown superior performance in many graph ML problems than traditional methods, and explaining them has attracted increased interest. However, GNN explanation for link prediction (LP) is lacking in the literature. LP is an essential GNN task and corresponds to web applications like recommendation and sponsored search on web. Given existing GNN explanation methods only address node/graph-level tasks, we propose Path-based GNN Explanation for heterogeneous Link prediction (PaGE-Link) that generates explanations with connection interpretability, enjoys model scalability, and handles graph heterogeneity. Qualitatively, PaGE-Link can generate explanations as paths connecting a node pair, which naturally captures connections between the two nodes and easily transfer to human-interpretable explanations. Quantitatively, explanations generated by PaGE-Link improve AUC for recommendation on citation and user-item graphs by 9 - 35% and are chosen as better by 78.79% of responses in human evaluation.