mlsanityData to 7 Oct 2026

View-based Explanations for Graph Neural Networks

arXiv 2401.02086 ↗First posted 4 Jan 2024cs.LG cs.DBcited by 8

Not on the map. Why?

Abstract (arXiv)

Generating explanations for graph neural networks (GNNs) has been studied to understand their behavior in analytical tasks such as graph classification. Existing approaches aim to understand the overall results of GNNs rather than providing explanations for specific class labels of interest, and may return explanation structures that are hard to access, nor directly queryable.We propose GVEX, a novel paradigm that generates Graph Views for EXplanation. (1) We design a two-tier explanation structure called explanation views. An explanation view consists of a set of graph patterns and a set of induced explanation subgraphs. Given a database G of multiple graphs and a specific class label l assigned by a GNN-based classifier M, it concisely describes the fraction of G that best explains why l is assigned by M. (2) We propose quality measures and formulate an optimization problem to compute optimal explanation views for GNN explanation. We show that the problem is Sigma2P-hard. (3) We present two algorithms. The first one follows an explain-and-summarize strategy that first generates high-quality explanation subgraphs which best explain GNNs in terms of feature influence maximization, and then performs a summarization step to generate patterns. We show that this strategy provides an approximation ratio of 1/2. Our second algorithm performs a single-pass to an input node stream in batches to incrementally maintain explanation views, having an anytime quality guarantee of 1/4 approximation. Using real-world benchmark data, we experimentally demonstrate the effectiveness, efficiency, and scalability of GVEX. Through case studies, we showcase the practical applications of GVEX.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 42 of its 79 references that are in the map. First posted on arXiv 4 Jan 2024.

Builds on

42 of 79 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  10. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  11. 2018Link Prediction Based on Graph Neural Networkscited by 829
  12. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
30 more
  1. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  2. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  3. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  4. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  5. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  6. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  7. 2018Graph Convolutional Networks for Text Classificationcited by 345
  8. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  9. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  10. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  11. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  12. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  13. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
  14. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  15. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  16. 2020A Large-Scale Database for Graph Representation Learningcited by 54
  17. 2021A Survey of Machine Learning for Computer Architecture and Systemscited by 53
  18. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  19. 2021Accelerating Large Scale Real-Time GNN Inference using Channel Pruningcited by 41
  20. 2021Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipeliningcited by 39
  21. 2019Layerwise Relevance Visualization in Convolutional Text Graph Classifierscited by 32
  22. 2021Explainable AI: current status and future directionscited by 32
  23. 2022Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysiscited by 32
  24. 2022Global Counterfactual Explainer for Graph Neural Networkscited by 30
  25. 2021Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximizationcited by 28
  26. 2020Fairness in Streaming Submodular Maximization: Algorithms and Hardnesscited by 23
  27. 2021Counterfactual Explanations for Machine Learning: Challenges Revisitedcited by 19
  28. 2013Submodular Maximization Meets Streaming: Matchings, Matroids, and Morecited by 14
  29. 2022Efficient Graph Neural Network Inference at Large Scalecited by 7
  30. 2021Automatic View Selection in Graph Databasescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 2.

8 papers.

  1. 2024Generating Robust Counterfactual Witnesses for Graph Neural Networkscited by 4
  2. 2026ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networkscited by 2
  3. 2025Deal: Distributed End-to-End GNN Inference for All Nodescited by 1
  4. 2025Finding Counterfactual Evidences for Node Classificationcited by 1
  5. 2025ML-Asset Management: Curation, Discovery, and Utilizationcited by 1
  6. 2025Interpreting Graph Inference with Skyline Explanationscited by 0
  7. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0
  8. 2026A Tight Expressivity Hierarchy for GNN-Based Entity Resolution in Master Data Managementcited by 0