# PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction

## TL;DR

PaGE-Link is a novel path-based explanation method for heterogeneous link prediction in GNNs, improving interpretability and model performance in recommendation tasks.

## Contribution

It introduces a scalable, path-based explanation approach for GNN link prediction that handles graph heterogeneity and enhances interpretability.

## Key findings

- Explanation paths improve AUC by 9-35% in recommendation tasks.
- 78.79% of human evaluators preferred PaGE-Link explanations.
- Method effectively captures connection interpretability in heterogeneous graphs.

## Abstract

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.