Welfare and Fairness Dynamics in Federated Learning: A Client Selection Perspective
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) is a privacy-preserving learning technique that enables distributed computing devices to train shared learning models across data silos collaboratively. Existing FL works mostly focus on designing advanced FL algorithms to improve the model performance. However, the economic considerations of the clients, such as fairness and incentive, are yet to be fully explored. Without such considerations, self-motivated clients may lose interest and leave the federation. To address this problem, we designed a novel incentive mechanism that involves a client selection process to remove low-quality clients and a money transfer process to ensure a fair reward distribution. Our experimental results strongly demonstrate that the proposed incentive mechanism can effectively improve the duration and fairness of the federation.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 53 references that are in the map. First posted on arXiv 17 Feb 2023.
Builds on
33 of 53 references.
References · 33
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
- 2018Federated Learning with Non-IID Datacited by 1,099
- 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
- 2018Federated Learning for Mobile Keyboard Predictioncited by 565
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
- 2019Federated Learning with Personalization Layerscited by 533
- 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
- 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
21 more
- 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
- 2018Scalable and accurate deep learning for electronic health recordscited by 275
- 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
- 2019Privacy-preserving Federated Brain Tumour Segmentationcited by 169
- 2019Federated Evaluation of On-device Personalizationcited by 147
- 2021Federated Learning for Open Bankingcited by 138
- 2018Blockchained On-Device Federated Learningcited by 105
- 2018In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learningcited by 80
- 2019Measure Contribution of Participants in Federated Learningcited by 78
- 2019Accelerating Federated Learning via Momentum Gradient Descentcited by 75
- 2021GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learningcited by 73
- 2019Active Federated Learningcited by 63
- 2020Federated Learning for Breast Density Classification: A Real-World Implementationcited by 62
- 2019Free-riders in Federated Learning: Attacks and Defensescited by 48
- 2020FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MECcited by 48
- 2019Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approachcited by 45
- 2019Abnormal Client Behavior Detection in Federated Learningcited by 39
- 2021A Comprehensive Survey of Incentive Mechanism for Federated Learningcited by 38
- 2018Towards Secure Blockchain-enabled Internet of Vehicles: Optimizing Consensus Management Using Reputation and Contract Theorycited by 14
- 2021Enabling Long-Term Cooperation in Cross-Silo Federated Learning: A Repeated Game Perspectivecited by 14
Built on by
Citing papers per year: 2023: 1.
1 paper.
- 2023Federated Learning with Convex Global and Local Constraints16 Oct 2023