# Just Train Twice: Improving Group Robustness without Training Group Information

arXiv: https://arxiv.org/abs/2107.09044 · HTML: https://mlsanity.com/paper/2107.09044/

## Key facts

- Cited by 523 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 63 references that are in the map.
- First posted on arXiv 19 Jul 2021.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)

## Built on by (most cited first, 30 of 523)

- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [Improving Out-of-Distribution Robustness via Selective Augmentation](https://mlsanity.com/paper/2201.00299/) (2022)
- [Simple data balancing achieves competitive worst-group-accuracy](https://mlsanity.com/paper/2110.14503/) (2021)
- [Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations](https://mlsanity.com/paper/2203.01517/) (2022)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning](https://mlsanity.com/paper/2204.08499/) (2022)
- [On Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2210.11369/) (2022)
- [Change is Hard: A Closer Look at Subpopulation Shift](https://mlsanity.com/paper/2302.12254/) (2023)
- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Test-Time Adaptation via Conjugate Pseudo-labels](https://mlsanity.com/paper/2207.09640/) (2022)
- [Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation](https://mlsanity.com/paper/2204.02070/) (2022)
- [Shortcut Learning of Large Language Models in Natural Language Understanding](https://mlsanity.com/paper/2208.11857/) (2022)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [Distilling Model Failures as Directions in Latent Space](https://mlsanity.com/paper/2206.14754/) (2022)
- [Perceptual Grouping in Contrastive Vision-Language Models](https://mlsanity.com/paper/2210.09996/) (2022)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Agree to Disagree: Diversity through Disagreement for Better Transferability](https://mlsanity.com/paper/2202.04414/) (2022)
- [Simple and Fast Group Robustness by Automatic Feature Reweighting](https://mlsanity.com/paper/2306.11074/) (2023)
- [MaskTune: Mitigating Spurious Correlations by Forcing to Explore](https://mlsanity.com/paper/2210.00055/) (2022)
- [Contrastive Adapters for Foundation Model Group Robustness](https://mlsanity.com/paper/2207.07180/) (2022)
- [Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2304.03322/) (2023)
- [Detecting Corrupted Labels Without Training a Model to Predict](https://mlsanity.com/paper/2110.06283/) (2021)
- [ZIN: When and How to Learn Invariance Without Environment Partition?](https://mlsanity.com/paper/2203.05818/) (2022)
- [Discovering and Mitigating Visual Biases through Keyword Explanation](https://mlsanity.com/paper/2301.11104/) (2023)
- [Diagnosing and Rectifying Vision Models using Language](https://mlsanity.com/paper/2302.04269/) (2023)

## Abstract (arXiv)

Standard training via empirical risk minimization (ERM) can produce models that achieve high accuracy on average but low accuracy on certain groups, especially in the presence of spurious correlations between the input and label. Prior approaches that achieve high worst-group accuracy, like group distributionally robust optimization (group DRO) require expensive group annotations for each training point, whereas approaches that do not use such group annotations typically achieve unsatisfactory worst-group accuracy. In this paper, we propose a simple two-stage approach, JTT, that first trains a standard ERM model for several epochs, and then trains a second model that upweights the training examples that the first model misclassified. Intuitively, this upweights examples from groups on which standard ERM models perform poorly, leading to improved worst-group performance. Averaged over four image classification and natural language processing tasks with spurious correlations, JTT closes 75% of the gap in worst-group accuracy between standard ERM and group DRO, while only requiring group annotations on a small validation set in order to tune hyperparameters.