mlsanityData to 7 Oct 2026

When is invariance useful in an Out-of-Distribution Generalization problem ?

arXiv 2008.01883 ↗First posted 4 Aug 2020stat.ML cs.LGcited by 52

Not on the map. Why?

Abstract (arXiv)

The goal of Out-of-Distribution (OOD) generalization problem is to train a predictor that generalizes on all environments. Popular approaches in this field use the hypothesis that such a predictor shall be an textitinvariant predictor that captures the mechanism that remains constant across environments. While these approaches have been experimentally successful in various case studies, there is still much room for the theoretical validation of this hypothesis. This paper presents a new set of theoretical conditions necessary for an invariant predictor to achieve the OOD optimality. Our theory not only applies to non-linear cases, but also generalizes the necessary condition used in citetrojas2018invariant. We also derive Inter Gradient Alignment algorithm from our theory and demonstrate its competitiveness on MNIST-derived benchmark datasets as well as on two of the three textitInvariance Unit Tests proposed by citetaubinlinear.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 13; 2023: 16; 2024: 12; 2025: 6; 2026: 3.

52 papers.

Sort:

By area:

  1. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  2. 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
  3. 2022Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shiftcited by 38
  4. 2021Quantifying and Improving Transferability in Domain Generalizationcited by 35
  5. 2022WOODS: Benchmarks for Out-of-Distribution Generalization in Time Seriescited by 29
  6. 2023Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalizationcited by 29
  7. 2023Domain Generalization in Computational Pathology: Survey and Guidelinescited by 29
  8. 2022Improving Multi-Task Generalization via Regularizing Spurious Correlationcited by 28
  9. 2022Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foregroundcited by 26
  10. 2024Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learningcited by 26
  11. 2023Distribution Shift Inversion for Out-of-Distribution Predictioncited by 23
  12. 2022Gradient Masked Averaging for Federated Learningcited by 22
38 more
  1. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 20
  2. 2023Domain Generalization via Rationale Invariancecited by 16
  3. 2023Understanding Hessian Alignment for Domain Generalizationcited by 15
  4. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12
  5. 2022When Neural Networks Fail to Generalize? A Model Sensitivity Perspectivecited by 10
  6. 2024Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shiftcited by 10
  7. 2023Hacking Task Confounder in Meta-Learningcited by 8
  8. 2023Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shiftscited by 7
  9. 2022OOD-Probe: A Neural Interpretation of Out-of-Domain Generalizationcited by 5
  10. 2022On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalizationcited by 5
  11. 2023An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibrationcited by 5
  12. 2023Causality-oriented robustness: exploiting general noise interventionscited by 5
  13. 2024Towards the Causal Complete Cause of Multi-Modal Representation Learningcited by 5
  14. 2022Regularization Penalty Optimization for Addressing Data Quality Variance in OoD Algorithmscited by 4
  15. 2024A Causal Inspired Early-Branching Structure for Domain Generalizationcited by 4
  16. 2023Domain Generalization without Excess Empirical Riskcited by 3
  17. 2024How Does Distribution Matching Help Domain Generalization: An Information-theoretic Analysiscited by 3
  18. 2024Benchmarking Domain Generalization Algorithms in Computational Pathologycited by 3
  19. 2024LLM Embeddings Improve Test-time Adaptation to Tabular Y|X-Shiftscited by 3
  20. 2024Generalizing to any diverse distribution: uniformity, gentle finetuning and rebalancingcited by 2
  21. 2025Federated Adapter on Foundation Models: An Out-Of-Distribution Approachcited by 2
  22. 2025Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergiescited by 2
  23. 2025Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalizationcited by 2
  24. 2022Invariance Learning based on Label Hierarchycited by 1
  25. 2022SparCAssist: A Model Risk Assessment Assistant Based on Sparse Generated Counterfactualscited by 1
  26. 2023A step towards the applicability of algorithms based on invariant causal learning on observational datacited by 1
  27. 2023Out-of-Distribution Optimality of Invariant Risk Minimizationcited by 1
  28. 2023Learning Invariant Representations with a Nonparametric Nadaraya-Watson Headcited by 1
  29. 2024Revisiting Spurious Correlation in Domain Generalizationcited by 1
  30. 2024Reducing Spurious Correlation for Federated Domain Generalizationcited by 1
  31. 2025Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sourcescited by 1
  32. 2026One-Step Generalization Ratio Guided Optimization for Domain Generalizationcited by 1
  33. 2021A call for better unit testing for invariant risk minimisationcited by 0
  34. 2023Global Layers: Non-IID Tabular Federated Learningcited by 0
  35. 2024Domain Agnostic Conditional Invariant Predictions for Domain Generalizationcited by 0
  36. 2024Utilizing Graph Generation for Enhanced Domain Adaptive Object Detectioncited by 0
  37. 2025Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text Embeddingscited by 0
  38. 2025Adapting, Fast and Slow: On Few-Shot Transportability of Compositionscited by 0

50 most cited of 52 All 52 (JSON)