AIMing for Standardised Explainability Evaluation in GNNs: A Framework and Case Study on Graph Kernel Networks

TL;DR

This paper introduces AIM, a flexible framework for evaluating the explainability of GNNs, demonstrated through case studies on graph kernel networks and prototype networks, leading to improved model interpretability.

Contribution

The paper presents AIM, a comprehensive, minimally constrained evaluation framework for GNN explainability, and applies it to analyze and enhance graph kernel networks.

Findings

AIM effectively measures explanation accuracy and interpretability at multiple levels.

Using AIM, the authors identified limitations in GKN explanations and developed xGKN with better explainability.

Case studies demonstrate AIM's utility in guiding model improvements.

Abstract

Graph Neural Networks (GNNs) have advanced significantly in handling graph-structured data, but a comprehensive framework for evaluating explainability remains lacking. Existing evaluation frameworks primarily involve post-hoc explanations, and operate in the setting where multiple methods generate a suite of explanations for a single model. This makes comparison of explanations across models difficult. Evaluation of inherently interpretable models often targets a specific aspect of interpretability relevant to the model, but remains underdeveloped in terms of generating insight across a suite of measures. We introduce AIM, a comprehensive framework that addresses these limitations by measuring Accuracy, Instance-level explanations, and Model-level explanations. AIM is formulated with minimal constraints to enhance flexibility and facilitate broad applicability. Here, we use AIM in a pipeline, extracting explanations from inherently interpretable GNNs such as graph kernel networks (GKNs) and prototype networks (PNs), evaluating these explanations with AIM, identifying their limitations and obtaining insights to their characteristics. Taking GKNs as a case study, we show how the insights obtained from AIM can be used to develop an updated model, xGKN, that maintains high accuracy while demonstrating improved explainability. Our approach aims to advance the field of Explainable AI (XAI) for GNNs, providing more robust and practical solutions for understanding and improving complex models.