Federated Learning with Fair Averaging

2021-04-30 · Zheng Wang, Xiaoliang Fan, Jianzhong Qi, Chenglu Wen, Cheng Wang, Rongshan Yu

Fairness has emerged as a critical problem in federated learning (FL). In this work, we identify a cause of unfairness in FL -- conflicting gradients with large differences in the magnitudes. To address this issue, we propose the federated fair averaging (FedFV) algorithm to mitigate potential conflicts among clients before averaging their gradients. We first use the cosine similarity to detect gradient conflicts, and then iteratively eliminate such conflicts by modifying both the direction and the magnitude of the gradients. We further show the theoretical foundation of FedFV to mitigate the issue conflicting gradients and converge to Pareto stationary solutions. Extensive experiments on a suite of federated datasets confirm that FedFV compares favorably against state-of-the-art methods in terms of fairness, accuracy and efficiency. The source code is available at https://github.com/WwZzz/easyFL.

📄 PDF Abstract BibTeX arXiv:2104.14937

Code (1)

WwZzz/easyFL 공식 구현 pytorch

Tasks

Fairness Federated Learning

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces

2023-11-03 · Aditya Desai, Benjamin Meisburger, Zichang Liu, Anshumali Shrivastava

Recommendation systems (RS) for items (e.g., movies, books) and ads are widely used to tailor content to users on various internet platforms. Traditionally, recommendation models are trained on a central server. However,…

Collaborative Filtering Federated Learning Recommendation Systems

Fairness-aware Federated Minimax Optimization with Convergence Guarantee

2023-07-10 · Gerry Windiarto Mohamad Dunda, Shenghui Song

Federated learning (FL) has garnered considerable attention due to its privacy-preserving feature. Nonetheless, the lack of freedom in managing user data can lead to group fairness issues, where models are biased towards…

Fairness Federated Learning Privacy Preserving

Federated Multi-Objective Learning with Controlled Pareto Frontiers

2025-08-07 · Jiansheng Rao, Jiayi Li, Zhizhi Gong, Soummya Kar 외 arxiv

Federated learning (FL) is a widely adopted paradigm for privacy-preserving model training, but FedAvg optimise for the majority while under-serving minority clients. Existing methods such as federated multi-objective le…

Federated Learning

FedPrune: Towards Inclusive Federated Learning

2021-10-27 · Muhammad Tahir Munir, Muhammad Mustansar Saeed, Mahad Ali, Zafar Ayyub Qazi 외

Federated learning (FL) is a distributed learning technique that trains a shared model over distributed data in a privacy-preserving manner. Unfortunately, FL's performance degrades when there is (i) variability in clien…

Fairness Federated Learning Privacy Preserving

Federated Asymptotics: a model to compare federated learning algorithms

2021-08-16 · Gary Cheng, Karan Chadha, John Duchi

We propose an asymptotic framework to analyze the performance of (personalized) federated learning algorithms. In this new framework, we formulate federated learning as a multi-criterion objective, where the goal is to m…

Federated Learning Meta-Learning Personalized Federated Learning