Data to 7 Oct 2026

Environment Inference for Invariant Learning

arXiv 2010.07249 ↗First posted 14 Oct 2020cs.LG cs.AIcited by 306

Not on the map. Why?

Abstract (arXiv)

Learning models that gracefully handle distribution shifts is central to research on domain generalization, robust optimization, and fairness. A promising formulation is domain-invariant learning, which identifies the key issue of learning which features are domain-specific versus domain-invariant. An important assumption in this area is that the training examples are partitioned into "domains" or "environments". Our focus is on the more common setting where such partitions are not provided. We propose EIIL, a general framework for domain-invariant learning that incorporates Environment Inference to directly infer partitions that are maximally informative for downstream Invariant Learning. We show that EIIL outperforms invariant learning methods on the CMNIST benchmark without using environment labels, and significantly outperforms ERM on worst-group performance in the Waterbirds and CivilComments datasets. Finally, we establish connections between EIIL and algorithmic fairness, which enables EIIL to improve accuracy and calibration in a fair prediction problem.

Key facts. Cited by 306 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 78; 2023: 71; 2024: 64; 2025: 46; 2026: 19.

306 papers.

Sort:

By area:

2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
2024Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Modelscited by 412
2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
2021Simple data balancing achieves competitive worst-group-accuracycited by 177
2022Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlationscited by 171
2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
2022On Feature Learning in the Presence of Spurious Correlationscited by 145

38 more

2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
2021Towards Principled Disentanglement for Domain Generalizationcited by 91
2021Heterogeneous Risk Minimizationcited by 90
2022Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimationcited by 88
2022A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Otherscited by 85
2022Perceptual Grouping in Contrastive Vision-Language Modelscited by 82
2021Causal Attention for Unbiased Visual Recognitioncited by 80
2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
2023Discover and Cure: Concept-aware Mitigation of Spurious Correlationcited by 71
2022Invariant Grounding for Video Question Answeringcited by 68
2022Contrastive Adapters for Foundation Model Group Robustnesscited by 62
2022ZIN: When and How to Learn Invariance Without Environment Partition?cited by 58
2022Diversify and Disambiguate: Learning From Underspecified Datacited by 55
2022Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesiscited by 54
2023Towards Last-layer Retraining for Group Robustness with Fewer Annotationscited by 54
2022Assaying Out-Of-Distribution Generalization in Transfer Learningcited by 53
2022Learning Debiased Classifier with Biased Committeecited by 51
2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
2023Mitigating Spurious Correlations in Multi-modal Models during Fine-tuningcited by 47
2021Learning Disentangled Representations in the Imaging Domaincited by 46
2022Diagnosing failures of fairness transfer across distribution shift in real-world medical settingscited by 45
2023MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoningcited by 45
2023Identifying Spurious Biases Early in Training through the Lens of Simplicity Biascited by 44
2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
2021Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlationscited by 41
2023Spawrious: A Benchmark for Fine Control of Spurious Correlation Biasescited by 41
2023Robust Learning with Progressive Data Expansion Against Spurious Correlationcited by 39
2024The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learningcited by 39
2022Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalizationcited by 38
2021Selective Regression Under Fairness Criteriacited by 34
2022Rich Feature Construction for the Optimization-Generalization Dilemmacited by 34
2022Invariant Feature Learning for Generalized Long-Tailed Classificationcited by 34
2023Mind the Label Shift of Augmentation-based Graph OOD Generalizationcited by 34
2022Identifying Weight-Variant Latent Causal Modelscited by 33
2023Free Lunch for Domain Adversarial Training: Environment Label Smoothingcited by 33
2022Learning Fair Representation via Distributional Contrastive Disentanglementcited by 31
2022On Learning Fairness and Accuracy on Multiple Subgroupscited by 31
2023Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropycited by 30

50 most cited of 306 All 306 (JSON)