Higher Order Structures For Graph Explanations

TL;DR

This paper introduces FORGE, a framework that enhances graph explainers by capturing higher-order multi-node interactions, significantly improving explanation accuracy for GNNs on real-world and synthetic datasets.

Contribution

The paper presents FORGE, a novel framework that incorporates higher-order structures into graph explanations, addressing limitations of existing explainers in modeling multi-node relationships.

Findings

FORGE improves explanation accuracy by 1.9x on real-world datasets.

FORGE enhances explanation accuracy by 2.25x on synthetic datasets.

Scalability analysis confirms FORGE's effectiveness on large graphs.

Abstract

Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations of graph-structured data, demonstrating remarkable performance across various tasks. Recognising their importance, there has been extensive research focused on explaining GNN predictions, aiming to enhance their interpretability and trustworthiness. However, GNNs and their explainers face a notable challenge: graphs are primarily designed to model pair-wise relationships between nodes, which can make it tough to capture higher-order, multi-node interactions. This characteristic can pose difficulties for existing explainers in fully representing multi-node relationships. To address this gap, we present Framework For Higher-Order Representations In Graph Explanations (FORGE), a framework that enables graph explainers to capture such interactions by incorporating higher-order structures, resulting in more accurate and faithful explanations. Extensive evaluation shows that on average real-world datasets from the GraphXAI benchmark and synthetic datasets across various graph explainers, FORGE improves average explanation accuracy by 1.9x and 2.25x, respectively. We perform ablation studies to confirm the importance of higher-order relations in improving explanations, while our scalability analysis demonstrates FORGE's efficacy on large graphs.