mlsanityData to 14 Oct 2026

Invariant Rationalization

arXiv 2003.09772 ↗First posted 22 Mar 2020cs.LG cs.AI cs.CLcited by 131

Not on the map. Why?

Abstract (arXiv)

Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction. A typical rationalization criterion, i.e. maximum mutual information (MMI), finds the rationale that maximizes the prediction performance based only on the rationale. However, MMI can be problematic because it picks up spurious correlations between the input features and the output. Instead, we introduce a game-theoretic invariant rationalization criterion where the rationales are constrained to enable the same predictor to be optimal across different environments. We show both theoretically and empirically that the proposed rationales can rule out spurious correlations, generalize better to different test scenarios, and align better with human judgments. Our data and code are available.

Key facts. Cited by 131 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 29; 2023: 36; 2024: 27; 2025: 11; 2026: 3.

131 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  2. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  3. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  4. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  5. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  6. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  7. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 164
  8. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  9. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 138
  10. 2021Does Invariant Risk Minimization Capture Invariance?cited by 116
  11. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  12. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
38 more
  1. 2021Heterogeneous Risk Minimizationcited by 90
  2. 2021Invariant Information Bottleneck for Domain Generalizationcited by 86
  3. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
  4. 2021Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?cited by 75
  5. 2022Graph Rationalization with Environment-based Augmentationscited by 70
  6. 2022ZIN: When and How to Learn Invariance Without Environment Partition?cited by 58
  7. 2022Let Invariant Rationale Discovery Inspire Graph Contrastive Learningcited by 57
  8. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  9. 2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
  10. 2023Model Agnostic Sample Reweighting for Out-of-Distribution Learningcited by 44
  11. 2024On Large Language Models' Hallucination with Regard to Known Factscited by 43
  12. 2021Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlationscited by 41
  13. 2022On the Explainability of Natural Language Processing Deep Modelscited by 38
  14. 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
  15. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  16. 2022Can Rationalization Improve Robustness?cited by 36
  17. 2023Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimizationcited by 29
  18. 2021Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fixcited by 27
  19. 2022Interpretable Geometric Deep Learning via Learnable Randomness Injectioncited by 27
  20. 2024Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learningcited by 27
  21. 2021Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanationscited by 26
  22. 2023Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalizationcited by 26
  23. 2021What to Learn, and How: Toward Effective Learning from Rationalescited by 25
  24. 2023Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domainscited by 24
  25. 2023Rationalization for Explainable NLP: A Surveycited by 22
  26. 2023Data-centric Graph Learning: A Surveycited by 22
  27. 2021Kernelized Heterogeneous Risk Minimizationcited by 21
  28. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 21
  29. 2023D-Separation for Causal Self-Explanationcited by 21
  30. 2021Rationalization through Conceptscited by 19
  31. 2021SPECTRA: Sparse Structured Text Rationalizationcited by 19
  32. 2022Localized Adversarial Domain Generalizationcited by 19
  33. 2023Towards Trustworthy Explanation: On Causal Rationalizationcited by 19
  34. 2023Diversifying Spatial-Temporal Perception for Video Domain Generalizationcited by 19
  35. 2024Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftscited by 19
  36. 2022FR: Folded Rationalization with a Unified Encodercited by 18
  37. 2021Learning Representations that Support Robust Transfer of Predictorscited by 17
  38. 2021Predict then Interpolate: A Simple Algorithm to Learn Stable Classifierscited by 16

50 most cited of 131 All 131 (JSON)