mlsanityData to 14 Oct 2026

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

arXiv 2605.14884 ↗First posted 14 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 14 May 2026.

Builds on

35 of 47 references.

References · 35

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2021How Attentive are Graph Attention Networks?cited by 835
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  7. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
  8. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  9. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  10. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  11. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  12. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
23 more
  1. 2020Graph Information Bottleneckcited by 168
  2. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
  3. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  4. 2022Evaluating Explainability for Graph Neural Networkscited by 87
  5. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  6. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  7. 2021Learning to Extend Molecular Scaffolds with Structural Motifscited by 71
  8. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 65
  9. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 64
  10. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 58
  11. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  12. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  13. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  14. 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 35
  15. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 35
  16. 2022Reinforced Causal Explainer for Graph Neural Networkscited by 34
  17. 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
  18. 2022GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendationscited by 22
  19. 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 17
  20. 2022Towards Prototype-Based Self-Explainable Graph Neural Networkcited by 14
  21. 2024GNNShap: Scalable and Accurate GNN Explanation using Shapley Valuescited by 12
  22. 2023D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusioncited by 9
  23. 2025Robustness questions the interpretability of graph neural networks: what to do?cited by 4

Built on by

Not cited yet.