Skip to main navigation Skip to search Skip to main content

Towards faithful class-level self-explainability in graph neural networks by subgraph dependencies

Research output: Contribution to journal › Article › peer-review

Abstract

Enhancing the interpretability of graph neural networks (GNNs) is crucial to ensure their safe and fair deployment. Recent work has introduced self-explainable GNNs that generate explanations as part of training, improving both faithfulness and efficiency. Some of these models, such as ProtGNN and PGIB, learn class-specific prototypes, offering a potential pathway toward class-level explanations. However, their evaluations focus solely on instance-level explanations, leaving open the question of whether these prototypes meaningfully generalize across instances of the same class. In this paper, we introduce GraphOracle, a novel self-explainable GNN framework designed to generate and evaluate class-level explanations for GNNs. Our model jointly learns a GNN classifier and a set of structured, sparse subgraphs that are discriminative for each class. We propose a novel integrated training that captures graph–subgraph–prediction dependencies efficiently and faithfully, validated through a masking-based evaluation strategy. This strategy enables us to retroactively assess whether prior methods like ProtGNN and PGIB deliver effective class-level explanations. Our results show that they do not. In contrast, GraphOracle achieves superior fidelity, explainability, and scalability across a range of graph classification tasks. We further demonstrate that GraphOracle avoids the computational bottlenecks of previous methods—like Monte Carlo Tree Search—by using entropy-regularized subgraph selection and lightweight random walk extraction, enabling faster and more scalable training. These findings position GraphOracle as a practical and principled solution for faithful class-level self-explainability in GNNs.

Original languageEnglish
JournalIEEE Transactions on Knowledge and Data Engineering
Early online date4 Sept 2026
DOIs
Publication statusE-pub ahead of print - 4 Sept 2026

Keywords

  • class-level explainability
  • faithfulness
  • Graph neural networks
  • subgraph dependencies

Fingerprint

Dive into the research topics of 'Towards faithful class-level self-explainability in graph neural networks by subgraph dependencies'. Together they form a unique fingerprint.

Cite this