GNN Explainability

GNN: Graph Neural Network

Ask about this topic

Overview

Graph neural network explainability seeks to show which node attributes, connections, subgraphs, or concepts drive predictions, including in temporal and heterogeneous graphs. Post-hoc approaches use masks, gradients, Shapley values, and counterfactual edits, while intrinsic methods build explanations into models through concept bottlenecks, sparse additive scores, or symbolic rules. Researchers evaluate explanations with fidelity, stability, sparsity, and ground-truth motifs on synthetic benchmarks as well as molecular, biological, and social-network tasks. A central challenge is that explanations can change with the explainer, graph structure, or evaluation metric, and a faithful account of model behavior does not by itself establish a causal or scientifically valid mechanism.

Latest papers

CardsList

82 papers10 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

  1. Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane

    Apr 28, 2026Pahal D. Patel, Sanmay GangulyGradient-Based AttributionJet Tagging

    Department of Physics, Indian Institute of Technology, Kanpur Uttar-Pradesh-208016, India

  2. Explaining Temporal Graph Predictions With Shapley Values

    Apr 27, 2026Lea-Marie Sussek, Stefan HeindorfTemporal GNNsShapley Value Attribution

    Paderborn University Paderborn, Germany

  3. Operational Feature Fingerprints of Graph Datasets via a White-Box Signal-Subspace Probe

    Apr 24, 2026Yuchen Xiong, Swee Keong Yeap, Zhen Hong BanGraph Signal ProcessingNode Classification

    China-ASEAN College of Marine Sciences · Xiamen University Malaysia · Sepang 43900, Selangor, Malaysia +1

  4. Mechanistic Interpretability Tool for AI Weather Models

    Apr 22, 2026Kirsten I. Tempest, Matthias Beylich, George C. CraigInterpretable MLMechanistic Interpretability

    Meteorological Institute Munich, Ludwig-Maximilians-Universität, 80333 Munich, Germany · Deutsches Zentrum für Luft- und Raumfahrt, Oberpfaffenhofen, Germany

  5. Concept Graph Convolutions: Message Passing in the Concept Space

    Apr 22, 2026Lucie Charlotte Magister, Pietro LioGraph Neural NetworksMessage Passing Neural Networks

    University of Cambridge

  6. TACENR: Task-Agnostic Contrastive Explanations for Node Representations

    Apr 21, 2026Vasiliki Papanikou, Evaggelia PitouraGraph Representation LearningGNN Explainability

    University of Ioannina, Greece · Archimedes/Athena Research Center, Greece

  7. Subgraph Concept Networks: Concept Levels in Graph Classification

    Apr 20, 2026Lucie Charlotte Magister, Alexander Norcliffe, Iulia Duta +1Graph Neural NetworksHierarchical Representation Learning

    University of Cambridge Cambridge, UK

  8. Explainable Graph Neural Networks for Interbank Contagion Surveillance: A Regulatory-Aligned Framework for the U.S. Banking Sector

    Apr 14, 2026Mohammad Nasir UddinSpatiotemporal GNNsGraph Attention Networks

    Data Analytics and Applied AI Researcher, Westcliff University, Irvine, CA, USA

  9. Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning

    Apr 13, 2026Xiaoxue Han, Libo Zhang, Zining Zhu +1GNN ExplainabilityText-Attributed Graph Learning

    Department of Computer Science, Stevens Institute of Technology, Hoboken, NJ, USA.

  10. Thermodynamic-Inspired Explainable GeoAI: Uncovering Regime-Dependent Mechanisms in Heterogeneous Spatial Systems

    Apr 6, 2026Sooyoung Lim, Zhenlong Li, Zi-Kui LiuPhase TransitionsGNN Explainability

    Geoinformation and Big Data Research Lab, Department of Geography, Pennsylvania State University, University Park, PA 16801, USA · Department of Materials Science and Engineering, Pennsylvania State University, University Park, PA 16801, USA

  11. LLM-Grounded Explainable AI for Supply Chain Risk Early Warning via Temporal Graph Attention Networks

    Mar 5, 2026Zhiming Xue, Yujue Wang, Menghao HuoSupply Chain ManagementLLM Reasoning with Graphs

    College of Engineering, Northeastern University, Boston, USA · Department of Chemistry and Chemical Biology, University of New Mexico, Albuquerque, USA · School of Engineering, Santa Clara University, Santa Clara, USA

  12. Beyond Edge Deletion: A Comprehensive Approach to Counterfactual Explanation in Graph Neural Networks

    Mar 4, 2026Matteo De Sanctis, Riccardo De Sanctis, Stefano Faralli +2GNN ExplainabilityCounterfactual Learning

    Sapienza University of Rome, Rome, Italy · ISTC-CNR & Sapienza University of Rome, Rome, Italy · Technical University of Munich, Munich, Germany

  13. EEG-SeeGraph: Interpreting functional connectivity disruptions in dementias via sparse-explanatory dynamic EEG-graph learning

    Mar 3, 2026Fengcheng Wu, Zhenxi Song, Guoyang Xu +4ElectroencephalographyDynamic Graph Learning

    Harbin Institute of Technology, Shenzhen, China · Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen · Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen, China

  14. Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer

    Mar 2, 2026Yue Niu, Zhaokai Sun, Jiayi Yang +5GNN ExplainabilityGraph Neural Networks

    Tongji University, Shanghai, China · City University of Macau, Macau, China

  15. BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loop

    Mar 2, 2026Chao Chen, Xujia Li, Dongsheng Hong +4Graph-Based Label PropagationGraph Representation Learning

    Harbin Institute of Technology (Shenzhen), Guangdong, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China · Fuzhou University, Fujian, China +1

  16. MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning

    Feb 24, 2026Jesse He, Helen Jenne, Max Vargas +4Neural Algorithmic ReasoningMechanistic Interpretability

    Pacific Northwest National Laboratory, Richland, WA · Halıcı˘oğlu Data Science Institute, University of California, San Diego, San Diego, CA · Department of Computer and Information Science, University of Pennsylvania, Pennsylvaina, PA +1

  17. Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls

    Feb 24, 2026Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas +2Generative ModelingGraph Clustering

    Yale Institute for Network Science, Yale University, USA · Universit´e Paris Saclay, Universit´e Paris Cit´e, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, France · ´Ecole Polytechnique, Paris, France +1

  18. Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection

    Feb 22, 2026Hossein Shokouhinejad, Roozbeh Razavi-Far, Griffin Higgins +1Mixture-of-Experts InterpretabilityMixture-of-Experts Models

    1*University of New Brunswick, Faculty of Computer Science, 3 Bailey Dr., Fredericton, E3B5A3, New Brunswick, Canada.

  19. Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning

    Feb 18, 2026Chuqin Geng, Li Zhang, Haolin Ye +5Graph Representation LearningGNN Explainability

    School of Computer Science, McGill University, Montreal, Canada · Department of Computer Science, University of Toronto, Toronto, Canada

  20. KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging

    Dec 8, 2025Md Raqibul Islam, Adrita Khan, Mir Sazzat Hossain +6Graph Representation LearningJet Tagging

    Center for Computational & Data Sciences, Independent University, Bangladesh, Dhaka-1229, Bangladesh · Department of Theoretical Physics, University of Dhaka, Dhaka-1000, Bangladesh · Department of Physical Sciences, Independent University, Bangladesh, Dhaka-1229, Bangladesh

  21. Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization

    Jul 4, 2025Zanyu Shi, Yang Wang, Pathum M. Weerawarna +4Protein-Ligand Binding Affinity PredictionMolecular Property Prediction

    Department of Biostatistics & Health Data Science, Indiana University Fairbanks School of Public Health, Indianapolis, 46202 IN, USA. · Department of Computer Science, Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington, Bloomington, 47405 IN, USA. · Division of Clinical Pharmacology, Indiana University School of Medicine, Indianapolis, 46202 IN, USA. +2

  22. RAW-Explainer: Post-hoc Explanations of Path Reasoning Graph Neural Networks for Knowledge Graph Completion

    Jun 14, 2025Ryoji Kubo, Samyam Lamichhane, Djellel DifallahGNN ExplainabilityGraph Neural Networks

    New York University Abu Dhabi, Abu Dhabi, United Arab Emirates