# Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks

arXiv: https://arxiv.org/abs/2304.03935 · HTML: https://mlsanity.com/paper/2304.03935/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 8 Apr 2023.

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

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [How Does Mixup Help With Robustness and Generalization?](https://mlsanity.com/paper/2010.04819/) (2020)
- [On the Apparent Conflict Between Individual and Group Fairness](https://mlsanity.com/paper/1912.06883/) (2019)
- [An Unconstrained Layer-Peeled Perspective on Neural Collapse](https://mlsanity.com/paper/2110.02796/) (2021)
- [Post-processing for Individual Fairness](https://mlsanity.com/paper/2110.13796/) (2021)
- [The Power of Contrast for Feature Learning: A Theoretical Analysis](https://mlsanity.com/paper/2110.02473/) (2021)
- [FNNC: Achieving Fairness through Neural Networks](https://mlsanity.com/paper/1811.00247/) (2018)
- [Toward Better Generalization Bounds with Locally Elastic Stability](https://mlsanity.com/paper/2010.13988/) (2020)
- [Adversarial Training Helps Transfer Learning via Better Representations](https://mlsanity.com/paper/2106.10189/) (2021)
- [Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations](https://mlsanity.com/paper/2006.11478/) (2020)
- [Improving Adversarial Robustness via Unlabeled Out-of-Domain Data](https://mlsanity.com/paper/2006.08476/) (2020)
- [Robustness Implies Generalization via Data-Dependent Generalization Bounds](https://mlsanity.com/paper/2206.13497/) (2022)
- [Technical Challenges for Training Fair Neural Networks](https://mlsanity.com/paper/2102.06764/) (2021)
- [FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data](https://mlsanity.com/paper/2206.02792/) (2022)
- [Understanding Dynamics of Nonlinear Representation Learning and Its Application](https://mlsanity.com/paper/2106.14836/) (2021)
- [README: REpresentation learning by fairness-Aware Disentangling MEthod](https://mlsanity.com/paper/2007.03775/) (2020)
- [Reinforcement Learning with Stepwise Fairness Constraints](https://mlsanity.com/paper/2211.03994/) (2022)
- [Scaffolding Sets](https://mlsanity.com/paper/2111.03135/) (2021)

## Built on by (most cited first, 17 of 17)

- [CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models](https://mlsanity.com/paper/2406.06007/) (2024)
- [Detecting High-Stakes Interactions with Activation Probes](https://mlsanity.com/paper/2506.10805/) (2025)
- [AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving](https://mlsanity.com/paper/2412.15206/) (2024)
- [Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization](https://mlsanity.com/paper/2402.12550/) (2024)
- [When is Multicalibration Post-Processing Necessary?](https://mlsanity.com/paper/2406.06487/) (2024)
- [Mind the Graph When Balancing Data for Fairness or Robustness](https://mlsanity.com/paper/2406.17433/) (2024)
- [A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models](https://mlsanity.com/paper/2401.03695/) (2024)
- [BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning](https://mlsanity.com/paper/2408.06890/) (2024)
- [Using Self-supervised Learning Can Improve Model Fairness](https://mlsanity.com/paper/2406.02361/) (2024)
- [Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities](https://mlsanity.com/paper/2406.01757/) (2024)
- [Looking Beyond What You See: An Empirical Analysis on Subgroup Intersectional Fairness for Multi-label Chest X-ray Classification Using Social Determinants of Racial Health Inequities](https://mlsanity.com/paper/2403.18196/) (2024)
- [AnyPcc: Compressing Any Point Cloud with a Single Universal Model](https://mlsanity.com/paper/2510.20331/) (2025)
- [The Fairness Stitch: Unveiling the Potential of Model Stitching in Neural Network De-Biasing](https://mlsanity.com/paper/2311.03532/) (2023)
- [Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation](https://mlsanity.com/paper/2410.05345/) (2024)
- [Fairness-Aware Low-Rank Representation Fine-Tuning](https://mlsanity.com/paper/2503.05684/) (2025)
- [SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation](https://mlsanity.com/paper/2508.18826/) (2025)
- [Beyond Demographic Balance: Multi-Metric and Intersectional Evaluation of Fairness in MIMIC-IV Mortality Prediction](https://mlsanity.com/paper/2610.01645/) (2026)

## Abstract (arXiv)

As machine learning has been deployed ubiquitously across applications in modern data science, algorithmic fairness has become a great concern. Among them, imposing fairness constraints during learning, i.e. in-processing fair training, has been a popular type of training method because they don't require accessing sensitive attributes during test time in contrast to post-processing methods. While this has been extensively studied in classical machine learning models, their impact on deep neural networks remains unclear. Recent research has shown that adding fairness constraints to the objective function leads to severe over-fitting to fairness criteria in large models, and how to solve this challenge is an important open question. To tackle this, we leverage the wisdom and power of pre-training and fine-tuning and develop a simple but novel framework to train fair neural networks in an efficient and inexpensive way -- last-layer fine-tuning alone can effectively promote fairness in deep neural networks. This framework offers valuable insights into representation learning for training fair neural networks.