mlsanityData to 7 Oct 2026

GPFL: A Gradient Projection-Based Client Selection Framework for Efficient Federated Learning

arXiv 2403.17833 ↗First posted 26 Mar 2024cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning client selection is crucial for determining participant clients while balancing model accuracy and communication efficiency. Existing methods have limitations in handling data heterogeneity, computational burdens, and independent client treatment. To address these challenges, we propose GPFL, which measures client value by comparing local and global descent directions. We also employ an Exploit-Explore mechanism to enhance performance. Experimental results on FEMINST and CIFAR-10 datasets demonstrate that GPFL outperforms baselines in Non-IID scenarios, achieving over 9% improvement in FEMINST test accuracy. Moreover, GPFL exhibits shorter computation times through pre-selection and parameter reuse in federated learning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 52 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

18 of 52 references.

References · 18

  1. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  2. 2018LEAF: A Benchmark for Federated Settingscited by 780
  3. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  4. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  5. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 247
  6. 2020An Improved Analysis of Stochastic Gradient Descent with Momentumcited by 117
  7. 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 102
  8. 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
  9. 2022Client Selection in Federated Learning: Principles, Challenges, and Opportunitiescited by 62
  10. 2020Fast-Convergent Federated Learningcited by 61
  11. 2021FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learningcited by 43
  12. 2020An Incentive Mechanism for Federated Learning in Wireless Cellular network: An Auction Approachcited by 39
6 more
  1. 2020Stochastic Client Selection for Federated Learning with Volatile Clientscited by 38
  2. 2021Game of Gradients: Mitigating Irrelevant Clients in Federated Learningcited by 35
  3. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  4. 2021Context-Aware Online Client Selection for Hierarchical Federated Learningcited by 20
  5. 2023FedSampling: A Better Sampling Strategy for Federated Learningcited by 8
  6. 2022ON-DEMAND-FL: A Dynamic and Efficient Multi-Criteria Federated Learning Client Deployment Schemecited by 7

Built on by

Not cited yet.