mlsanityData to 14 Oct 2026

MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation

arXiv 2307.07832 ↗First posted 15 Jul 2023cs.LG cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. However, their predictions are often not interpretable. Post-hoc instance-level explanation methods have been proposed to understand GNN predictions. These methods seek to discover substructures that explain the prediction behavior of a trained GNN. In this paper, we shed light on the existence of the distribution shifting issue in existing methods, which affects explanation quality, particularly in applications on real-life datasets with tight decision boundaries. To address this issue, we introduce a generalized Graph Information Bottleneck (GIB) form that includes a label-independent graph variable, which is equivalent to the vanilla GIB. Driven by the generalized GIB, we propose a graph mixup method, MixupExplainer, with a theoretical guarantee to resolve the distribution shifting issue. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness of our proposed mixup approach over existing approaches. We also provide a detailed analysis of how our proposed approach alleviates the distribution shifting issue.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 35 of its 58 references that are in the map. First posted on arXiv 15 Jul 2023.

Builds on

35 of 58 references.

References · 35

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  7. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  8. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  9. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  11. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  12. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
23 more
  1. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  2. 2015Diffusion-Convolutional Neural Networkscited by 268
  3. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 213
  4. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  5. 2020Graph Information Bottleneckcited by 168
  6. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
  7. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 146
  8. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  9. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  10. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  11. 2019Concrete Autoencoders for Differentiable Feature Selection and Reconstructioncited by 90
  12. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
  13. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  14. 2022Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labelscited by 63
  15. 2022C-Mixup: Improving Generalization in Regressioncited by 57
  16. 2021GraphMixup: Improving Class-Imbalanced Node Classification on Graphs by Self-supervised Context Predictioncited by 36
  17. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 35
  18. 2018Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answeringcited by 30
  19. 2022A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metricscited by 26
  20. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  21. 2021A Meta-Learning Approach for Training Explainable Graph Neural Networkscited by 15
  22. 2022Towards Faithful and Consistent Explanations for Graph Neural Networkscited by 13
  23. 2022Modeling Network-level Traffic Flow Transitions on Sparse Datacited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 6; 2026: 3.

18 papers.

Sort:

By area:

  1. 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 17
  2. 2024A Graph is Worth K Words: Euclideanizing Graph using Pure Transformercited by 10
  3. 2023Factorized Explainer for Graph Neural Networkscited by 8
  4. 2024LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generationcited by 8
  5. 2024Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanationcited by 6
  6. 2024Powerformer: A Section-adaptive Transformer for Power Flow Adjustmentcited by 5
  7. 2025SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extractioncited by 5
  8. 2025FROG: Fair Removal on Graphscited by 4
  9. 2026Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architecturescited by 4
  10. 2024Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networkscited by 3
  11. 2025RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanationcited by 3
  12. 2025Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networkscited by 2
6 more
  1. 2024Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learningcited by 1
  2. 2024REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretabilitycited by 0
  3. 2025From Binary to Continuous: Stochastic Re-Weighting for Robust Graph Explanationcited by 0
  4. 2025Explainable Graph Representation Learning via Graph Pattern Analysiscited by 0
  5. 2026Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainabilitycited by 0
  6. 2026NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruptioncited by 0