# Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learning

arXiv: https://arxiv.org/abs/2504.21775 · HTML: https://mlsanity.com/paper/2504.21775/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Builds on (most cited first, 22 of 22)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Federated Learning for Internet of Things: A Comprehensive Survey](https://mlsanity.com/paper/2104.07914/) (2021)
- [A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic](https://mlsanity.com/paper/2007.05170/) (2020)
- [FairFed: Enabling Group Fairness in Federated Learning](https://mlsanity.com/paper/2110.00857/) (2021)
- [Distributionally Robust Federated Averaging](https://mlsanity.com/paper/2102.12660/) (2021)
- [FairBatch: Batch Selection for Model Fairness](https://mlsanity.com/paper/2012.01696/) (2020)
- [Collaborative Fairness in Federated Learning](https://mlsanity.com/paper/2008.12161/) (2020)
- [Fairness-aware Agnostic Federated Learning](https://mlsanity.com/paper/2010.05057/) (2020)
- [Federated Learning with Fair Averaging](https://mlsanity.com/paper/2104.14937/) (2021)
- [Pareto Set Learning for Neural Multi-objective Combinatorial Optimization](https://mlsanity.com/paper/2203.15386/) (2022)
- [Improving Fairness via Federated Learning](https://mlsanity.com/paper/2110.15545/) (2021)
- [ProPublica's COMPAS Data Revisited](https://mlsanity.com/paper/1906.04711/) (2019)
- [GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learning](https://mlsanity.com/paper/2108.02741/) (2021)
- [FAIR-FATE: Fair Federated Learning with Momentum](https://mlsanity.com/paper/2209.13678/) (2022)
- [PraFFL: A Preference-Aware Scheme in Fair Federated Learning](https://mlsanity.com/paper/2404.08973/) (2024)
- [Achieving Fairness Across Local and Global Models in Federated Learning](https://mlsanity.com/paper/2406.17102/) (2024)

## Abstract (arXiv)

Recent methods leverage a hypernet to handle the performance-fairness trade-offs in federated learning. This hypernet maps the clients' preferences between model performance and fairness to preference-specifc models on the trade-off curve, known as local Pareto front. However, existing methods typically adopt a uniform preference sampling distribution to train the hypernet across clients, neglecting the inherent heterogeneity of their local Pareto fronts. Meanwhile, from the perspective of generalization, they do not consider the gap between local and global Pareto fronts on the global dataset. To address these limitations, we propose HetPFL to effectively learn both local and global Pareto fronts. HetPFL comprises Preference Sampling Adaptation (PSA) and Preference-aware Hypernet Fusion (PHF). PSA adaptively determines the optimal preference sampling distribution for each client to accommodate heterogeneous local Pareto fronts. While PHF performs preference-aware fusion of clients' hypernets to ensure the performance of the global Pareto front. We prove that HetPFL converges linearly with respect to the number of rounds, under weaker assumptions than existing methods. Extensive experiments on four datasets show that HetPFL significantly outperforms seven baselines in terms of the quality of learned local and global Pareto fronts.