# Fairness-Aware Meta-Learning via Nash Bargaining

arXiv: https://arxiv.org/abs/2406.07029 · HTML: https://mlsanity.com/paper/2406.07029/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 57 references that are in the map.
- First posted on arXiv 11 Jun 2024.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Multi-Task Learning as a Bargaining Game](https://mlsanity.com/paper/2202.01017/) (2022)
- [DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks](https://mlsanity.com/paper/2110.12884/) (2021)
- [Generalized Inner Loop Meta-Learning](https://mlsanity.com/paper/1910.01727/) (2019)
- [Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AI](https://mlsanity.com/paper/2005.05906/) (2020)
- [Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation](https://mlsanity.com/paper/2305.02231/) (2023)
- [Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective](https://mlsanity.com/paper/2308.13985/) (2023)
- [First-order methods almost always avoid saddle points: the case of vanishing step-sizes](https://mlsanity.com/paper/1906.07772/) (2019)
- [FAE: A Fairness-Aware Ensemble Framework](https://mlsanity.com/paper/2002.00695/) (2020)
- [Fair Exploration via Axiomatic Bargaining](https://mlsanity.com/paper/2106.02553/) (2021)
- [Comprehensive Fair Meta-learned Recommender System](https://mlsanity.com/paper/2206.04789/) (2022)
- [How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?](https://mlsanity.com/paper/2210.06516/) (2022)
- [Understanding bias in facial recognition technologies](https://mlsanity.com/paper/2010.07023/) (2020)
- [Proxy Non-Discrimination in Data-Driven Systems](https://mlsanity.com/paper/1707.08120/) (2017)
- [The Kalai-Smorodinski solution for many-objective Bayesian optimization](https://mlsanity.com/paper/1902.06565/) (2019)
- [FORML: Learning to Reweight Data for Fairness](https://mlsanity.com/paper/2202.01719/) (2022)
- [Multi-Issue Bargaining With Deep Reinforcement Learning](https://mlsanity.com/paper/2002.07788/) (2020)
- [Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music](https://mlsanity.com/paper/2203.13422/) (2022)

## Built on by (most cited first, 6 of 6)

- [MUNBa: Machine Unlearning via Nash Bargaining](https://mlsanity.com/paper/2411.15537/) (2024)
- [FEED: Fairness-Enhanced Meta-Learning for Domain Generalization](https://mlsanity.com/paper/2411.01316/) (2024)
- [FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning](https://mlsanity.com/paper/2506.03777/) (2025)
- [From Competition to Collaboration: Designing Sustainable Mechanisms Between LLMs and Online Forums](https://mlsanity.com/paper/2602.04572/) (2026)
- [S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF](https://mlsanity.com/paper/2607.18258/) (2026)
- [Learning Through Game: Skewed Transfer of Tabular Knowledge to Strengthen Image Model](https://mlsanity.com/paper/2609.32272/) (2026)

## Abstract (arXiv)

To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set. Such an adjustment procedure can be cast within a meta-learning framework. However, naive integration of fairness goals via meta-learning can cause hypergradient conflicts for subgroups, resulting in unstable convergence and compromising model performance and fairness. To navigate this issue, we frame the resolution of hypergradient conflicts as a multi-player cooperative bargaining game. We introduce a two-stage meta-learning framework in which the first stage involves the use of a Nash Bargaining Solution (NBS) to resolve hypergradient conflicts and steer the model toward the Pareto front, and the second stage optimizes with respect to specific fairness goals. Our method is supported by theoretical results, notably a proof of the NBS for gradient aggregation free from linear independence assumptions, a proof of Pareto improvement, and a proof of monotonic improvement in validation loss. We also show empirical effects across various fairness objectives in six key fairness datasets and two image classification tasks.