# Towards Last-layer Retraining for Group Robustness with Fewer Annotations

arXiv: https://arxiv.org/abs/2309.08534 · HTML: https://mlsanity.com/paper/2309.08534/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 83 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## Builds on (most cited first, 30 of 55)

- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [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)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [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)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [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)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning](https://mlsanity.com/paper/1412.6614/) (2014)
- [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)
- [Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging](https://mlsanity.com/paper/1909.12475/) (2019)
- [Probing Neural Network Comprehension of Natural Language Arguments](https://mlsanity.com/paper/1907.07355/) (2019)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)

## Built on by (most cited first, 30 of 54)

- [On the Foundations of Shortcut Learning](https://mlsanity.com/paper/2310.16228/) (2023)
- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation](https://mlsanity.com/paper/2403.05171/) (2024)
- [Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations](https://mlsanity.com/paper/2403.07241/) (2024)
- [Discovering environments with XRM](https://mlsanity.com/paper/2309.16748/) (2023)
- [The Pitfalls of Memorization: When Memorization Hurts Generalization](https://mlsanity.com/paper/2412.07684/) (2024)
- [When is Multicalibration Post-Processing Necessary?](https://mlsanity.com/paper/2406.06487/) (2024)
- [FRAPPE: A Group Fairness Framework for Post-Processing Everything](https://mlsanity.com/paper/2312.02592/) (2023)
- [Intermediate Layer Classifiers for OOD generalization](https://mlsanity.com/paper/2504.05461/) (2025)
- [Real-Time Aligned Reward Model beyond Semantics](https://mlsanity.com/paper/2601.22664/) (2026)
- [Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2403.03375/) (2024)
- [Mind the Graph When Balancing Data for Fairness or Robustness](https://mlsanity.com/paper/2406.17433/) (2024)
- [Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations](https://mlsanity.com/paper/2407.14974/) (2024)
- [Peer-to-Peer Learning Dynamics of Wide Neural Networks](https://mlsanity.com/paper/2409.15267/) (2024)
- [Efficient Bias Mitigation Without Privileged Information](https://mlsanity.com/paper/2409.17691/) (2024)
- [Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets](https://mlsanity.com/paper/2510.02818/) (2025)
- [Robustness to Subpopulation Shift with Domain Label Noise via Regularized Annotation of Domains](https://mlsanity.com/paper/2402.11039/) (2024)
- [The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations](https://mlsanity.com/paper/2407.13957/) (2024)
- [Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions](https://mlsanity.com/paper/2503.07315/) (2025)
- [Adaptive Group Robust Ensemble Knowledge Distillation](https://mlsanity.com/paper/2411.14984/) (2024)
- [Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift](https://mlsanity.com/paper/2505.23027/) (2025)
- [Theoretical Guarantees of Data Augmented Last Layer Retraining Methods](https://mlsanity.com/paper/2405.05934/) (2024)
- [Optimizing importance weighting in the presence of sub-population shifts](https://mlsanity.com/paper/2410.14315/) (2024)
- [Improving Group Robustness on Spurious Correlation via Evidential Alignment](https://mlsanity.com/paper/2506.11347/) (2025)
- [On the Unreasonable Effectiveness of Last-layer Retraining](https://mlsanity.com/paper/2512.01766/) (2025)
- [AdaFlood: Adaptive Flood Regularization](https://mlsanity.com/paper/2311.02891/) (2023)
- [TLDR: Text Based Last-layer Retraining for Debiasing Image Classifiers](https://mlsanity.com/paper/2311.18291/) (2023)
- [NeuronTune: Towards Self-Guided Spurious Bias Mitigation](https://mlsanity.com/paper/2505.24048/) (2025)
- [Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation](https://mlsanity.com/paper/2506.02294/) (2025)
- [Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation](https://mlsanity.com/paper/2508.08570/) (2025)

## Abstract (arXiv)

Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious correlations and poor generalization on minority groups. The recent deep feature reweighting (DFR) technique achieves state-of-the-art group robustness via simple last-layer retraining, but it requires held-out group and class annotations to construct a group-balanced reweighting dataset. In this work, we examine this impractical requirement and find that last-layer retraining can be surprisingly effective with no group annotations (other than for model selection) and only a handful of class annotations. We first show that last-layer retraining can greatly improve worst-group accuracy even when the reweighting dataset has only a small proportion of worst-group data. This implies a "free lunch" where holding out a subset of training data to retrain the last layer can substantially outperform ERM on the entire dataset with no additional data or annotations. To further improve group robustness, we introduce a lightweight method called selective last-layer finetuning (SELF), which constructs the reweighting dataset using misclassifications or disagreements. Our empirical and theoretical results present the first evidence that model disagreement upsamples worst-group data, enabling SELF to nearly match DFR on four well-established benchmarks across vision and language tasks with no group annotations and less than 3% of the held-out class annotations. Our code is available at https://github.com/tmlabonte/last-layer-retraining.