Federating for Learning Group Fair Models
Not on the map. Why?
Abstract (arXiv)
Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minmax group fairness in paradigms where different participating entities may only have access to a subset of the population groups during the training phase. We formally analyze how this fairness objective differs from existing federated learning fairness criteria that impose similar performance across participants instead of demographic groups. We provide an optimization algorithm -- FedMinMax -- for solving the proposed problem that provably enjoys the performance guarantees of centralized learning algorithms. We experimentally compare the proposed approach against other methods in terms of group fairness in various federated learning setups.
Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 5 Oct 2021.
Builds on
14 of 24 references.
References · 14
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2016Equality of Opportunity in Supervised Learningcited by 2,007
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
- 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
- 2019Agnostic Federated Learningcited by 456
- 2019Fair Resource Allocation in Federated Learningcited by 394
- 2015The Variational Fair Autoencodercited by 223
- 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 153
- 2020Tilted Empirical Risk Minimizationcited by 106
- 2021Distributionally Robust Federated Averagingcited by 104
2 more
- 2017Robust Optimization for Non-Convex Objectivescited by 35
- 2020Minimax Group Fairness: Algorithms and Experimentscited by 17
Built on by
Citing papers per year: 2021: 1; 2022: 4; 2023: 2; 2024: 2.
9 papers.
- 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
- 2022Fairness in Federated Learning via Core-Stabilitycited by 23
- 2022Local Stochastic Bilevel Optimization with Momentum-Based Variance Reductioncited by 20
- 2022PrivFairFL: Privacy-Preserving Group Fairness in Federated Learningcited by 13
- 2023Bias Propagation in Federated Learningcited by 12
- 2021Models of fairness in federated learningcited by 8
- 2022FedDAR: Federated Domain-Aware Representation Learningcited by 8
- 2024Achieving Fairness Across Local and Global Models in Federated Learningcited by 5
- 2024Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clusteringcited by 1
- 2024Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clustering27 Jul 2024
- 2024Achieving Fairness Across Local and Global Models in Federated Learning24 Jun 2024
- 2023Bias Propagation in Federated Learning5 Sep 2023
- 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-off25 Jun 2023
- 2022Fairness in Federated Learning via Core-Stability3 Nov 2022
- 2022FedDAR: Federated Domain-Aware Representation Learning8 Sep 2022
- 2022PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning23 May 2022
- 2022Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction3 May 2022
- 2021Models of fairness in federated learning1 Dec 2021