Higher Order Structures For Graph Explanations

2024-06-05

AI Summary

Graph Neural Network (GNN) explainers struggle to model multi-node higher-order interactions, limiting explanation fidelity and accuracy. To address this, we propose FORGE—a novel framework that systematically integrates higher-order combinatorial structures, specifically hypergraphs and simplicial complexes, into the GNN explanation pipeline for the first time. FORGE employs differentiable higher-order structure encoding to explicitly capture collaborative decision-making mechanisms and supports plug-and-play integration with mainstream explainers such as GNNExplainer and PGM-Explainer. Evaluated on the real-world GraphXAI benchmark, FORGE achieves a 1.9× average improvement in explanation accuracy; on synthetic benchmarks, the gain reaches 2.25×. Our core contribution lies in pioneering the incorporation of higher-order topological structures to enhance GNN interpretability—bridging rigorous theoretical foundations with practical engineering deployability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Graph Neural Networks
• Interpretability
• Accuracy

Innovation

• FORGE framework
• Graph Neural Networks (GNNs)
• Interpretability enhancement