mlsanityData to 14 Oct 2026

Interpretable Geometric Deep Learning via Learnable Randomness Injection

arXiv 2210.16966 ↗First posted 30 Oct 2022cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Point cloud data is ubiquitous in scientific fields. Recently, geometric deep learning (GDL) has been widely applied to solve prediction tasks with such data. However, GDL models are often complicated and hardly interpretable, which poses concerns to scientists who are to deploy these models in scientific analysis and experiments. This work proposes a general mechanism, learnable randomness injection (LRI), which allows building inherently interpretable models based on general GDL backbones. LRI-induced models, once trained, can detect the points in the point cloud data that carry information indicative of the prediction label. We also propose four datasets from real scientific applications that cover the domains of high-energy physics and biochemistry to evaluate the LRI mechanism. Compared with previous post-hoc interpretation methods, the points detected by LRI align much better and stabler with the ground-truth patterns that have actual scientific meanings. LRI is grounded by the information bottleneck principle, and thus LRI-induced models are also more robust to distribution shifts between training and test scenarios. Our code and datasets are available at urlhttps://github.com/Graph-COM/LRI.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 68 of its 108 references that are in the map. First posted on arXiv 30 Oct 2022.

Builds on

68 of 108 references.

References · 68

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Graph Attention Networkscited by 8,923
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  7. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  9. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  10. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  11. 2018How Powerful are Graph Neural Networks?cited by 4,393
  12. 2017Axiomatic Attribution for Deep Networkscited by 3,384
38 more
  1. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  2. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  3. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  5. 2019Invariant Risk Minimizationcited by 1,854
  6. 2020Point Transformercited by 1,470
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  8. 2017Deep Setscited by 1,421
  9. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  10. 2016Group Equivariant Convolutional Networkscited by 1,165
  11. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  12. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  13. 2021E(n) Equivariant Graph Neural Networkscited by 965
  14. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  15. 2016Deep Variational Information Bottleneckcited by 930
  16. 2019Attention is not Explanationcited by 929
  17. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  18. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  19. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  20. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  21. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  22. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  23. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  24. 2020Directional Message Passing for Molecular Graphscited by 561
  25. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  26. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  27. 2019Is Attention Interpretable?cited by 389
  28. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  29. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  30. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  31. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 215
  32. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  33. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  34. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  35. 2020Graph Information Bottleneckcited by 168
  36. 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 166
  37. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  38. 2022EquiBind: Geometric Deep Learning for Drug Binding Structure Predictioncited by 144

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 10; 2024: 7; 2025: 7; 2026: 2.

27 papers.

Sort:

  1. 2023Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistencycited by 42
  2. 2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
  3. 2023A Survey on Explainability of Graph Neural Networkscited by 29
  4. 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discoverycited by 27
  5. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  6. 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 17
  7. 2024Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNscited by 16
  8. 2024How Interpretable Are Interpretable Graph Neural Networks?cited by 13
  9. 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspectivecited by 11
  10. 2023Learning High-Order Relationships of Brain Regionscited by 10
  11. 2023Factorized Explainer for Graph Neural Networkscited by 8
  12. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 7
15 more
  1. 2023How Faithful are Self-Explainable GNNs?cited by 5
  2. 2025SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extractioncited by 5
  3. 2026GNN Explanations that do not Explain and How to find Themcited by 5
  4. 2022FAIR AI Models in High Energy Physicscited by 4
  5. 2023GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shiftscited by 4
  6. 2025RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanationcited by 3
  7. 2023Joint Feature and Differentiable k -NN Graph Learning using Dirichlet Energycited by 1
  8. 2024Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic reviewcited by 1
  9. 2024Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learningcited by 1
  10. 2024Transformers from Diffusion: A Unified Framework for Neural Message Passingcited by 1
  11. 2024Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learningcited by 1
  12. 2025XAI for Point Cloud Data using Perturbations based on Meaningful Segmentationcited by 1
  13. 2025Learning Invariant Graph Representations Through Redundant Informationcited by 1
  14. 2024PAC Learnability under Explanation-Preserving Graph Perturbationscited by 0
  15. 2026Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learningcited by 0