mlsanityData to 14 Oct 2026

Combating Client Dropout in Federated Learning via Friend Model Substitution

arXiv 2205.13222 ↗First posted 26 May 2022cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a new distributed machine learning framework known for its benefits on data privacy and communication efficiency. Since full client participation in many cases is infeasible due to constrained resources, partial participation FL algorithms have been investigated that proactively select/sample a subset of clients, aiming to achieve learning performance close to the full participation case. This paper studies a passive partial client participation scenario that is much less well understood, where partial participation is a result of external events, namely client dropout, rather than a decision of the FL algorithm. We cast FL with client dropout as a special case of a larger class of FL problems where clients can submit substitute (possibly inaccurate) local model updates. Based on our convergence analysis, we develop a new algorithm FL-FDMS that discovers friends of clients (i.e., clients whose data distributions are similar) on-the-fly and uses friends' local updates as substitutes for the dropout clients, thereby reducing the substitution error and improving the convergence performance. A complexity reduction mechanism is also incorporated into FL-FDMS, making it both theoretically sound and practically useful. Experiments on MNIST and CIFAR-10 confirmed the superior performance of FL-FDMS in handling client dropout in FL.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 30 of its 36 references that are in the map. First posted on arXiv 26 May 2022.

Builds on

30 of 36 references.

References · 30

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  5. 2018Federated Learning with Non-IID Datacited by 1,108
  6. 2020Adaptive Federated Optimizationcited by 1,046
  7. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  8. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  9. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  10. 2018Sparsified SGD with Memorycited by 376
  11. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 278
  12. 2019Asynchronous Federated Optimizationcited by 267
18 more
  1. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 243
  2. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
  3. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 193
  4. 2019On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimizationcited by 180
  5. 2019SCAFFOLD: Stochastic Controlled Averaging for Federated Learningcited by 175
  6. 2020Optimal Client Sampling for Federated Learningcited by 124
  7. 2018Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithmscited by 106
  8. 2021Heterogeneity for the Win: One-Shot Federated Clusteringcited by 87
  9. 2019SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overheadcited by 82
  10. 2021Fast Federated Learning in the Presence of Arbitrary Device Unavailabilitycited by 72
  11. 2020Towards Flexible Device Participation in Federated Learningcited by 65
  12. 2020Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneitycited by 56
  13. 2021FedSoft: Soft Clustered Federated Learning with Proximal Local Updatingcited by 46
  14. 2021Anarchic Federated Learningcited by 42
  15. 2020Communication-Efficient Federated Learning via Optimal Client Samplingcited by 39
  16. 2021Node Selection Toward Faster Convergence for Federated Learning on Non-IID Datacited by 39
  17. 2020Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availabilitycited by 20
  18. 2019Asynchronous Federated Learning with Differential Privacy for Edge Intelligencecited by 16

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2023MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updatescited by 10
  2. 2024QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learningcited by 2
  3. 2025Overcoming Challenges of Partial Client Participation in Federated Learning : A Comprehensive Reviewcited by 0