mlsanityData to 14 Oct 2026

B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data

arXiv 2505.22252 ↗First posted 28 May 2025cs.LG cs.CEcited by 4

Not on the map. Why?

Abstract (arXiv)

Understanding the reasoning behind deep learning model predictions is crucial in cheminformatics and drug discovery, where molecular design determines their properties. However, current evaluation frameworks for Explainable AI (XAI) in this domain often rely on artificial datasets or simplified tasks, employing data-derived metrics that fail to capture the complexity of real-world scenarios and lack a direct link to explanation faithfulness. To address this, we introduce B-XAIC, a novel benchmark constructed from real-world molecular data and diverse tasks with known ground-truth rationales for assigned labels. Through a comprehensive evaluation using B-XAIC, we reveal limitations of existing XAI methods for Graph Neural Networks (GNNs) in the molecular domain. This benchmark provides a valuable resource for gaining deeper insights into the faithfulness of XAI, facilitating the development of more reliable and interpretable models.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

36 of 52 references.

References · 36

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  5. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  7. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  8. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  9. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  10. 2016Not Just a Black Box: Learning Important Features Through Propagating Activation Differencescited by 297
  11. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  12. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
24 more
  1. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  2. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  3. 2020Graph Information Bottleneckcited by 168
  4. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  5. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  6. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
  7. 2020Drug discovery with explainable artificial intelligencecited by 118
  8. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  9. 2022Evaluating Explainability for Graph Neural Networkscited by 87
  10. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  11. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  12. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  13. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 65
  14. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 58
  15. 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
  16. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  17. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  18. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 35
  19. 2018Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistrycited by 25
  20. 2022GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendationscited by 22
  21. 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 17
  22. 2021Graph Kernel Neural Networkscited by 13
  23. 2022ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Predictioncited by 8
  24. 2025This looks like what? Challenges and Future Research Directions for Part-Prototype Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysiscited by 1
  2. 2026FORGE: Fragment-Oriented Ranking and Generation for Context-Aware Molecular Optimizationcited by 0
  3. 2026Measuring What Matters: A Unified Evaluation Framework for GNN Explainabilitycited by 0
  4. 2026WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testingcited by 0