Evaluating Link Prediction Explanations for Graph Neural Networks

TL;DR

This paper introduces quantitative metrics to evaluate the quality of link prediction explanations in Graph Neural Networks, addressing a gap in validation methods and analyzing how technical choices affect explanation quality.

Contribution

It proposes new metrics for assessing link prediction explanations and evaluates existing explainability methods using these metrics, considering task-specific factors.

Findings

Metrics effectively quantify explanation quality.

Explainability methods vary in performance.

Technical choices impact explanation effectiveness.

Abstract

Graph Machine Learning (GML) has numerous applications, such as node/graph classification and link prediction, in real-world domains. Providing human-understandable explanations for GML models is a challenging yet fundamental task to foster their adoption, but validating explanations for link prediction models has received little attention. In this paper, we provide quantitative metrics to assess the quality of link prediction explanations, with or without ground-truth. State-of-the-art explainability methods for Graph Neural Networks are evaluated using these metrics. We discuss how underlying assumptions and technical details specific to the link prediction task, such as the choice of distance between node embeddings, can influence the quality of the explanations.