# Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach

arXiv: https://arxiv.org/abs/2303.03300 · HTML: https://mlsanity.com/paper/2303.03300/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 63 references that are in the map.
- First posted on arXiv 6 Mar 2023.

## Builds on (most cited first, 30 of 37)

- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [Towards Understanding Sharpness-Aware Minimization](https://mlsanity.com/paper/2206.06232/) (2022)
- [Efficient Sharpness-aware Minimization for Improved Training of Neural Networks](https://mlsanity.com/paper/2110.03141/) (2021)
- [Towards a Unified Framework for Fair and Stable Graph Representation Learning](https://mlsanity.com/paper/2102.13186/) (2021)
- [Fair Mixup: Fairness via Interpolation](https://mlsanity.com/paper/2103.06503/) (2021)
- [Training individually fair ML models with Sensitive Subspace Robustness](https://mlsanity.com/paper/1907.00020/) (2019)
- [Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Support](https://mlsanity.com/paper/2112.05675/) (2021)
- [Robust Fairness under Covariate Shift](https://mlsanity.com/paper/2010.05166/) (2020)
- [Learning to Pivot with Adversarial Networks](https://mlsanity.com/paper/1611.01046/) (2016)
- [Two Simple Ways to Learn Individual Fairness Metrics from Data](https://mlsanity.com/paper/2006.11439/) (2020)
- [Predicting Out-of-Distribution Error with the Projection Norm](https://mlsanity.com/paper/2202.05834/) (2022)
- [A Short-term Intervention for Long-term Fairness in the Labor Market](https://mlsanity.com/paper/1712.00064/) (2017)
- [Algorithmic Fairness in Education](https://mlsanity.com/paper/2007.05443/) (2020)
- [SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness](https://mlsanity.com/paper/2006.14168/) (2020)
- [FMP: Toward Fair Graph Message Passing against Topology Bias](https://mlsanity.com/paper/2202.04187/) (2022)
- [Addressing Fairness in Classification with a Model-Agnostic Multi-Objective Algorithm](https://mlsanity.com/paper/2009.04441/) (2020)
- [Fair Classification with Adversarial Perturbations](https://mlsanity.com/paper/2106.05964/) (2021)
- [Transferring Fairness under Distribution Shifts via Fair Consistency Regularization](https://mlsanity.com/paper/2206.12796/) (2022)
- [Counterfactual Fairness with Partially Known Causal Graph](https://mlsanity.com/paper/2205.13972/) (2022)

## Built on by (most cited first, 12 of 12)

- [Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing](https://mlsanity.com/paper/2406.05534/) (2024)
- [SparseDM: Toward Sparse Efficient Diffusion Models](https://mlsanity.com/paper/2404.10445/) (2024)
- [Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium](https://mlsanity.com/paper/2410.16432/) (2024)
- [Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains](https://mlsanity.com/paper/2402.14145/) (2024)
- [Enhancing Group Fairness in Online Settings Using Oblique Decision Forests](https://mlsanity.com/paper/2310.11401/) (2023)
- [On the Maximal Local Disparity of Fairness-Aware Classifiers](https://mlsanity.com/paper/2406.03255/) (2024)
- [Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience](https://mlsanity.com/paper/2308.03175/) (2023)
- [Navigating Towards Fairness with Data Selection](https://mlsanity.com/paper/2412.11072/) (2024)
- [A Flat Minima Perspective on Understanding Augmentations and Model Robustness](https://mlsanity.com/paper/2505.24592/) (2025)
- [Testing for Causal Fairness](https://mlsanity.com/paper/2502.12874/) (2025)
- [DGSAM: Domain Generalization via Individual Sharpness-Aware Minimization](https://mlsanity.com/paper/2503.23430/) (2025)
- [A Comprehensive View of Fairness through Distributional Stability](https://mlsanity.com/paper/2609.37061/) (2026)

## Abstract (arXiv)

Fairness in machine learning has attracted increasing attention in recent years. The fairness methods improving algorithmic fairness for in-distribution data may not perform well under distribution shifts. In this paper, we first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. Subsequently, we analyze the sufficient conditions to guarantee fairness (i.e., low demographic parity) for the target dataset, including fairness for the source dataset, and low prediction difference between the source and target datasets for each sensitive attribute group. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR) by considering the worst case within the model weight perturbation ball for each sensitive attribute group. We evaluate the effectiveness of our proposed RFR algorithm on synthetic and real distribution shifts across various datasets. Experimental results demonstrate that RFR achieves better fairness-accuracy trade-off performance compared with several baselines. The source code is available at urlhttps://github.com/zhimengj0326/RFRNeurIPS23.