GRAFT: Auditing Graph Neural Networks via Global Feature Attribution

TL;DR

GRAFT is a novel framework for globally explaining GNN predictions by identifying class-level feature importance, using attribution, exemplar selection, and language models for natural language rule generation.

Contribution

It introduces GRAFT, combining attribution, exemplar selection, and language models to produce interpretable, class-level feature importance explanations for GNNs.

Findings

GRAFT effectively captures model-relevant features across datasets and architectures.

It supports bias analysis and feature-efficient transfer learning.

Human evaluation shows generated rules are accurate and useful.

Abstract

Graph Neural Networks (GNNs) achieve strong performance on node classification tasks but remain difficult to interpret, particularly with respect to which input features drive their predictions. Existing global GNN explainers operate at the structural level identifying recurring subgraph motifs, but none explain model behaviour globally at the level of input node attributes. We propose GRAFT, a posthoc global explanation framework that identifies class-level feature importance profiles for GNNs. The method combines diversity-guided exemplar selection, Integrated Gradients-based attribution, and aggregation to construct a global view of feature influence for each class, which can be further expressed as concise natural language rules using a large language model with self-refinement. We evaluate GRAFT across multiple datasets, architectures, and experimental settings, demonstrating its effectiveness in capturing model-relevant features, supporting bias analysis, and enabling feature-efficient transfer learning. In addition, we introduce a structured human evaluation protocol to assess the interpretability of generated rules along dimensions such as accuracy and usefulness. Our results suggest that GRAFT provides a practical and interpretable approach for analysing feature-level behaviour in GNNs, bridging quantitative attribution with human-understandable explanations.