mlsanityData to 7 Oct 2026

Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation

arXiv 2405.02745 ↗First posted 4 May 2024cs.LG cs.DCcited by 3

Not on the map. Why?

Abstract (arXiv)

Existing works in federated learning (FL) often assume an ideal system with either full client or uniformly distributed client participation. However, in practice, it has been observed that some clients may never participate in FL training (aka incomplete client participation) due to a myriad of system heterogeneity factors. A popular approach to mitigate impacts of incomplete client participation is the server-assisted federated learning (SA-FL) framework, where the server is equipped with an auxiliary dataset. However, despite SA-FL has been empirically shown to be effective in addressing the incomplete client participation problem, there remains a lack of theoretical understanding for SA-FL. Meanwhile, the ramifications of incomplete client participation in conventional FL are also poorly understood. These theoretical gaps motivate us to rigorously investigate SA-FL. Toward this end, we first show that conventional FL is em not PAC-learnable under incomplete client participation in the worst case. Then, we show that the PAC-learnability of FL with incomplete client participation can indeed be revived by SA-FL, which theoretically justifies the use of SA-FL for the first time. Lastly, to provide practical guidance for SA-FL training under em incomplete client participation, we propose the mathsfSAFARI (server-assisted federated averaging) algorithm that enjoys the same linear convergence speedup guarantees as classic FL with ideal client participation assumptions, offering the first SA-FL algorithm with convergence guarantee. Extensive experiments on different datasets show mathsfSAFARI significantly improves the performance under incomplete client participation.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 4 May 2024.

Builds on

33 of 55 references.

References · 33

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  5. 2018Federated Learning with Non-IID Datacited by 1,099
  6. 2020Adaptive Federated Optimizationcited by 1,036
  7. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  8. 2019Towards Federated Learning at Scale: System Designcited by 826
  9. 2014Convex Optimization: Algorithms and Complexitycited by 569
  10. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  11. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  12. 2021A Field Guide to Federated Optimizationcited by 312
21 more
  1. 2019Asynchronous Federated Optimizationcited by 264
  2. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  3. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 192
  4. 2022ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!cited by 134
  5. 2020Optimal Client Sampling for Federated Learningcited by 123
  6. 2021Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradientscited by 122
  7. 2019Measure Contribution of Participants in Federated Learningcited by 78
  8. 2022Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learningcited by 76
  9. 2021Fast Federated Learning in the Presence of Arbitrary Device Unavailabilitycited by 72
  10. 2020On the Value of Target Data in Transfer Learningcited by 62
  11. 2022A Unified Analysis of Federated Learning with Arbitrary Client Participationcited by 45
  12. 2021STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learningcited by 43
  13. 2021Anarchic Federated Learningcited by 42
  14. 2023On the Convergence of Federated Averaging with Cyclic Client Participationcited by 31
  15. 2021Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learningcited by 30
  16. 2020A No-Free-Lunch Theorem for MultiTask Learningcited by 28
  17. 2015Refined Error Bounds for Several Learning Algorithmscited by 24
  18. 2021Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfercited by 23
  19. 2022Can 5th Generation Local Training Methods Support Client Sampling? Yes!cited by 22
  20. 2023Federated Learning with Regularized Client Participationcited by 13
  21. 2020On the Sample Complexity of Adversarial Multi-Source PAC Learningcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026BiCoLoR: Communication-Efficient Optimization with Bidirectional Compression and Local Trainingcited by 1
  2. 2025Overcoming Challenges of Partial Client Participation in Federated Learning : A Comprehensive Reviewcited by 0
  3. 2026FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networkscited by 0