Towards Automated Evaluation of Explanations in Graph Neural Networks

TL;DR

This paper proposes automatic evaluation methods for explanations of Graph Neural Networks, aiming to improve how explanations are assessed for clarity and usefulness in real-world AI applications.

Contribution

It introduces novel automatic evaluation approaches for GNN explanations, addressing the gap in assessing explanation quality from a user-centric perspective.

Findings

Proposed new evaluation metrics for GNN explanations

Demonstrated effectiveness of methods on real-world datasets

Enhanced understanding of explanation quality assessment

Abstract

Explaining Graph Neural Networks predictions to end users of AI applications in easily understandable terms remains an unsolved problem. In particular, we do not have well developed methods for automatically evaluating explanations, in ways that are closer to how users consume those explanations. Based on recent application trends and our own experiences in real world problems, we propose automatic evaluation approaches for GNN Explanations.