mlsanityData to 7 Oct 2026

An Empirical Study of Invariant Risk Minimization

arXiv 2004.05007 ↗First posted 10 Apr 2020stat.ML cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

Invariant risk minimization (IRM) (Arjovsky et al., 2019) is a recently proposed framework designed for learning predictors that are invariant to spurious correlations across different training environments. Yet, despite its theoretical justifications, IRM has not been extensively tested across various settings. In an attempt to gain a better understanding of the framework, we empirically investigate several research questions using IRMv1, which is the first practical algorithm proposed to approximately solve IRM. By extending the ColoredMNIST experiment in different ways, we find that IRMv1 (i) performs better as the spurious correlation varies more widely between training environments, (ii) learns an approximately invariant predictor when the underlying relationship is approximately invariant, and (iii) can be extended to an analogous setting for text classification.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 8; 2023: 8; 2024: 6; 2025: 2; 2026: 2.

35 papers.

Sort:

By area:

  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  2. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  3. 2022ZIN: When and How to Learn Invariance Without Environment Partition?cited by 58
  4. 2022Bayesian Prompt Learning for Image-Language Model Generalizationcited by 51
  5. 2023Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignmentcited by 47
  6. 2023Model Agnostic Sample Reweighting for Out-of-Distribution Learningcited by 43
  7. 2021An Empirical Framework for Domain Generalization in Clinical Settingscited by 32
  8. 2024DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detectioncited by 28
  9. 2021Predict then Interpolate: A Simple Algorithm to Learn Stable Classifierscited by 16
  10. 2021Are Bias Mitigation Techniques for Deep Learning Effective?cited by 14
  11. 2022FL Games: A Federated Learning Framework for Distribution Shiftscited by 14
  12. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12
23 more
  1. 2022OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypothesescited by 11
  2. 2022An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentationcited by 11
  3. 2021Detecting Spurious Correlations with Sanity Tests for Artificial Intelligence Guided Radiology Systemscited by 10
  4. 2023What Is Missing in IRM Training and Evaluation? Challenges and Solutionscited by 10
  5. 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directionscited by 9
  6. 2022FedGen: Generalizable Federated Learning for Sequential Datacited by 9
  7. 2021Meta-Learned Invariant Risk Minimizationcited by 7
  8. 2021Causal Learning for Socially Responsible AIcited by 7
  9. 2021Contextualizing Meta-Learning via Learning to Decomposecited by 5
  10. 2025DADM: Dual Alignment of Domain and Modality for Face Anti-spoofingcited by 4
  11. 2023Environment Diversification with Multi-head Neural Network for Invariant Learningcited by 3
  12. 2023Multi-dimensional domain generalization with low-rank structurescited by 2
  13. 2023Out-of-Distribution Generalization in Text Classification: Past, Present, and Futurecited by 1
  14. 2023Invariant Representation via Decoupling Style and Spurious Features from Imagescited by 1
  15. 2024Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rulecited by 1
  16. 2026PEPR: Privileged Event-based Predictive Regularization for Domain Generalizationcited by 1
  17. 2022FL Games: A federated learning framework for distribution shiftscited by 0
  18. 2024FAIRM: Learning invariant representations for algorithmic fairness and domain generalization with minimax optimalitycited by 0
  19. 2024Domain Agnostic Conditional Invariant Predictions for Domain Generalizationcited by 0
  20. 2024Disentangled Representations for Causal Cognitioncited by 0
  21. 2024Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environmentscited by 0
  22. 2025A Probabilistic Framework for Temporal Distribution Generalization in Industry-Scale Recommender Systemscited by 0
  23. 2026Towards Context-Invariant Safety Alignment for Large Language Modelscited by 0