mlsanityData to 7 Oct 2026

Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks

arXiv 2404.13804 ↗First posted 22 Apr 2024cs.DC cs.LG cs.NIcited by 9

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) algorithms usually sample a fraction of clients in each round (partial participation) when the number of participants is large and the server's communication bandwidth is limited. Recent works on the convergence analysis of FL have focused on unbiased client sampling, e.g., sampling uniformly at random, which suffers from slow wall-clock time for convergence due to high degrees of system heterogeneity and statistical heterogeneity. This paper aims to design an adaptive client sampling algorithm for FL over wireless networks that tackles both system and statistical heterogeneity to minimize the wall-clock convergence time. We obtain a new tractable convergence bound for FL algorithms with arbitrary client sampling probability. Based on the bound, we analytically establish the relationship between the total learning time and sampling probability with an adaptive bandwidth allocation scheme, which results in a non-convex optimization problem. We design an efficient algorithm for learning the unknown parameters in the convergence bound and develop a low-complexity algorithm to approximately solve the non-convex problem. Our solution reveals the impact of system and statistical heterogeneity parameters on the optimal client sampling design. Moreover, our solution shows that as the number of sampled clients increases, the total convergence time first decreases and then increases because a larger sampling number reduces the number of rounds for convergence but results in a longer expected time per-round due to limited wireless bandwidth. Experimental results from both hardware prototype and simulation demonstrate that our proposed sampling scheme significantly reduces the convergence time compared to several baseline sampling schemes.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 38 of its 52 references that are in the map. First posted on arXiv 22 Apr 2024.

Builds on

38 of 52 references.

References · 38

  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. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  7. 2019Towards Federated Learning at Scale: System Designcited by 826
  8. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  9. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  10. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  11. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
  12. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 192
26 more
  1. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  2. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  3. 2019On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimizationcited by 178
  4. 2019SCAFFOLD: Stochastic Controlled Averaging for Federated Learningcited by 174
  5. 2019On the Convergence of Local Descent Methods in Federated Learningcited by 150
  6. 2013Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithmcited by 132
  7. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  8. 2020Optimal Client Sampling for Federated Learningcited by 123
  9. 2020TiFL: A Tier-based Federated Learning Systemcited by 95
  10. 2021Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learningcited by 93
  11. 2014Stochastic Optimization with Importance Samplingcited by 91
  12. 2018Wireless Network Intelligence at the Edgecited by 90
  13. 2020Convergence Time Optimization for Federated Learning over Wireless Networkscited by 81
  14. 2015Variance Reduction in SGD by Distributed Importance Samplingcited by 79
  15. 2018Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGDcited by 76
  16. 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
  17. 2020Fast-Convergent Federated Learningcited by 61
  18. 2020Cost-Effective Federated Learning Designcited by 61
  19. 2020Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneitycited by 56
  20. 2019Device Scheduling with Fast Convergence for Wireless Federated Learningcited by 46
  21. 2021Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementationcited by 40
  22. 2020Network-Aware Optimization of Distributed Learning for Fog Computingcited by 27
  23. 2020Federated Learning under Importance Samplingcited by 26
  24. 2017Safe Adaptive Importance Samplingcited by 19
  25. 2017BLENDER: Enabling Local Search with a Hybrid Differential Privacy Modelcited by 14
  26. 2021Joint Coding and Scheduling Optimization for Distributed Learning over Wireless Edge Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 4.

9 papers.

  1. 2025Federated Learning-Distillation Alternation for Resource-Constrained IoTcited by 2
  2. 2025FedCGD: Collective Gradient Divergence Optimized Scheduling for Wireless Federated Learningcited by 2
  3. 2025Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approachcited by 0
  4. 2025A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Controlcited by 0
  5. 2025Tackling Heterogeneity in Federated Learning via Variance-Reduced Boltzmann Sampling within Homogeneous Social Coalitionscited by 0
  6. 2026Towards Performance-Enhanced Model-Contrastive Federated Learning using Historical Information in Heterogeneous Scenarioscited by 0
  7. 2026Tackling Privacy Heterogeneity in Differentially Private Federated Learningcited by 0
  8. 2026FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learningcited by 0
  9. 2026Polar Code Based Federated Learning: Convergence Analysis and Resource Allocationcited by 0