# When Does Group Invariant Learning Survive Spurious Correlations?

arXiv: https://arxiv.org/abs/2206.14534 · HTML: https://mlsanity.com/paper/2206.14534/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 29 Jun 2022.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [The Risks of Invariant Risk Minimization](https://mlsanity.com/paper/2010.05761/) (2020)
- [Domain Generalization using Causal Matching](https://mlsanity.com/paper/2006.07500/) (2020)
- [Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.06607/) (2021)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [On Calibration and Out-of-domain Generalization](https://mlsanity.com/paper/2102.10395/) (2021)
- [End-to-End Bias Mitigation by Modelling Biases in Corpora](https://mlsanity.com/paper/1909.06321/) (2019)
- [Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime](https://mlsanity.com/paper/1810.02575/) (2018)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [Heterogeneous Risk Minimization](https://mlsanity.com/paper/2105.03818/) (2021)
- [Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance](https://mlsanity.com/paper/2005.00315/) (2020)
- [Empirical or Invariant Risk Minimization? A Sample Complexity Perspective](https://mlsanity.com/paper/2010.16412/) (2020)
- [Causally motivated Shortcut Removal Using Auxiliary Labels](https://mlsanity.com/paper/2105.06422/) (2021)
- [Unshuffling Data for Improved Generalization](https://mlsanity.com/paper/2002.11894/) (2020)
- [HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference](https://mlsanity.com/paper/2003.02756/) (2020)
- [Uncertainty Calibration for Ensemble-Based Debiasing Methods](https://mlsanity.com/paper/2111.04104/) (2021)

## Built on by (most cited first, 18 of 18)

- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization](https://mlsanity.com/paper/2306.01103/) (2023)
- [Improving Generalization of Alignment with Human Preferences through Group Invariant Learning](https://mlsanity.com/paper/2310.11971/) (2023)
- [Group Robust Classification Without Any Group Information](https://mlsanity.com/paper/2310.18555/) (2023)
- [Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization](https://mlsanity.com/paper/2306.02595/) (2023)
- [Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization](https://mlsanity.com/paper/2306.08076/) (2023)
- [One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes](https://mlsanity.com/paper/2406.13544/) (2024)
- [Understanding Domain Generalization: A Noise Robustness Perspective](https://mlsanity.com/paper/2401.14846/) (2024)
- [IDEA: Invariant Defense for Graph Adversarial Robustness](https://mlsanity.com/paper/2305.15792/) (2023)
- [InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models](https://mlsanity.com/paper/2412.08480/) (2024)
- [TIF: Learning Temporal Invariance in Android Malware Detectors](https://mlsanity.com/paper/2502.05098/) (2025)
- [Disentangled Representation Learning with Transmitted Information Bottleneck](https://mlsanity.com/paper/2311.01686/) (2023)
- [Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization](https://mlsanity.com/paper/2305.12123/) (2023)
- [OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?](https://mlsanity.com/paper/2410.02735/) (2024)
- [Why Domain Generalization Fail? A View of Necessity and Sufficiency](https://mlsanity.com/paper/2502.10716/) (2025)
- [Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies](https://mlsanity.com/paper/2505.22829/) (2025)
- [Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study](https://mlsanity.com/paper/2602.18502/) (2026)
- [From Objectives to What Models Learn: A Landau Theory of Invariant Learning](https://mlsanity.com/paper/2608.09396/) (2026)

## Abstract (arXiv)

By inferring latent groups in the training data, recent works introduce invariant learning to the case where environment annotations are unavailable. Typically, learning group invariance under a majority/minority split is empirically shown to be effective in improving out-of-distribution generalization on many datasets. However, theoretical guarantee for these methods on learning invariant mechanisms is lacking. In this paper, we reveal the insufficiency of existing group invariant learning methods in preventing classifiers from depending on spurious correlations in the training set. Specifically, we propose two criteria on judging such sufficiency. Theoretically and empirically, we show that existing methods can violate both criteria and thus fail in generalizing to spurious correlation shifts. Motivated by this, we design a new group invariant learning method, which constructs groups with statistical independence tests, and reweights samples by group label proportion to meet the criteria. Experiments on both synthetic and real data demonstrate that the new method significantly outperforms existing group invariant learning methods in generalizing to spurious correlation shifts.