paper-with-me

홈 › Papers

FedFair^3: Unlocking Threefold Fairness in Federated Learning

2024-01-29 · Simin Javaherian, Sanjeev Panta, Shelby Williams, Md Sirajul Islam, Li Chen

Federated Learning (FL) is an emerging paradigm in machine learning without exposing clients' raw data. In practical scenarios with numerous clients, encouraging fair and efficient client participation in federated learning is of utmost importance, which is also challenging given the heterogeneity in data distribution and device properties. Existing works have proposed different client-selection methods that consider fairness; however, they fail to select clients with high utilities while simultaneously achieving fair accuracy levels. In this paper, we propose a fair client-selection approach that unlocks threefold fairness in federated learning. In addition to having a fair client-selection strategy, we enforce an equitable number of rounds for client participation and ensure a fair accuracy distribution over the clients. The experimental results demonstrate that FedFair^3, in comparison to the state-of-the-art baselines, achieves 18.15% less accuracy variance on the IID data and 54.78% on the non-IID data, without decreasing the global accuracy. Furthermore, it shows 24.36% less wall-clock training time on average.

📄 PDF Abstract BibTeX arXiv:2401.16350

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessFederated Learning

Similar Papers 제목 키워드 기반

pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learning

2025-03-19 · Haoyu Lei, Shizhan Gong, Qi Dou, Farzan Farnia

Federated learning (FL) algorithms commonly aim to maximize clients' accuracy by training a model on their collective data. However, in several FL applications, the model's decisions should meet a group fairness constrai…

FairnessFederated LearningPersonalized Federated Learning

Privacy-Preserving Federated Learning for Fair and Efficient Urban Traffic Optimization

2025-11-09 · Rathin Chandra Shit, Sharmila Subudhi arxiv

The optimization of urban traffic is threatened by the complexity of achieving a balance between transport efficiency and the maintenance of privacy, as well as the equitable distribution of traffic based on socioeconomi…

Federated Learning

Training Fair Models in Federated Learning without Data Privacy Infringement

2021-09-13 · Xin Che, Jingdi Hu, Zirui Zhou, Yong Zhang 외

Training fair machine learning models becomes more and more important. As many powerful models are trained by collaboration among multiple parties, each holding some sensitive data, it is natural to explore the feasibili…

FairnessFederated Learning

Fair Concurrent Training of Multiple Models in Federated Learning

2024-04-22 · Marie Siew, Haoran Zhang, Jong-Ik Park, Yuezhou Liu 외

Federated learning (FL) enables collaborative learning across multiple clients. In most FL work, all clients train a single learning task. However, the recent proliferation of FL applications may increasingly require mul…

FairnessFederated Learning

Distribution-Free Fair Federated Learning with Small Samples

2024-02-25 · Qichuan Yin, Zexian Wang, Junzhou Huang, Huaxiu Yao 외

As federated learning gains increasing importance in real-world applications due to its capacity for decentralized data training, addressing fairness concerns across demographic groups becomes critically important. Howev…

FairnessFederated Learning