mlsanityData to 7 Oct 2026

A Unified Analysis of Federated Learning with Arbitrary Client Participation

arXiv 2205.13648 ↗First posted 26 May 2022cs.LG cs.DC cs.ITcited by 45

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) faces challenges of intermittent client availability and computation/communication efficiency. As a result, only a small subset of clients can participate in FL at a given time. It is important to understand how partial client participation affects convergence, but most existing works have either considered idealized participation patterns or obtained results with non-zero optimality error for generic patterns. In this paper, we provide a unified convergence analysis for FL with arbitrary client participation. We first introduce a generalized version of federated averaging (FedAvg) that amplifies parameter updates at an interval of multiple FL rounds. Then, we present a novel analysis that captures the effect of client participation in a single term. By analyzing this term, we obtain convergence upper bounds for a wide range of participation patterns, including both non-stochastic and stochastic cases, which match either the lower bound of stochastic gradient descent (SGD) or the state-of-the-art results in specific settings. We also discuss various insights, recommendations, and experimental results.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 26 May 2022.

Builds on

33 of 47 references.

References · 33

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  7. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  8. 2020Adaptive Federated Optimizationcited by 1,036
  9. 2019Towards Federated Learning at Scale: System Designcited by 826
  10. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  11. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 333
  12. 2019Lower Bounds for Non-Convex Stochastic Optimizationcited by 303
21 more
  1. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 277
  2. 2019SGD: General Analysis and Improved Ratescited by 206
  3. 2018Don't Use Large Mini-Batches, Use Local SGDcited by 201
  4. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 192
  5. 2019On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimizationcited by 178
  6. 2020Is Local SGD Better than Minibatch SGD?cited by 151
  7. 2020Minibatch vs Local SGD for Heterogeneous Distributed Learningcited by 147
  8. 2020Optimal Client Sampling for Federated Learningcited by 123
  9. 2020Random Reshuffling: Simple Analysis with Vast Improvementscited by 112
  10. 2019Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronizationcited by 106
  11. 2021Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learningcited by 93
  12. 2020Local SGD: Unified Theory and New Efficient Methodscited by 88
  13. 2015Why Random Reshuffling Beats Stochastic Gradient Descentcited by 78
  14. 2018Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGDcited by 76
  15. 2021Fast Federated Learning in the Presence of Arbitrary Device Unavailabilitycited by 72
  16. 2020Towards Flexible Device Participation in Federated Learningcited by 64
  17. 2021Anarchic Federated Learningcited by 42
  18. 2019Semi-Cyclic Stochastic Gradient Descentcited by 40
  19. 2021Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyondcited by 35
  20. 2020Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availabilitycited by 20
  21. 2020Distributed Optimization over Block-Cyclic Datacited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 19; 2025: 8; 2026: 5.

45 papers.

Sort:

  1. 2023On the Convergence of Federated Averaging with Cyclic Client Participationcited by 31
  2. 2022DELTA: Diverse Client Sampling for Fasting Federated Learningcited by 24
  3. 2023Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reductioncited by 24
  4. 2023Accelerating Hybrid Federated Learning Convergence under Partial Participationcited by 15
  5. 2023Federated Learning with Regularized Client Participationcited by 13
  6. 2023MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updatescited by 10
  7. 2023Federated Learning with Instance-Dependent Noisy Labelcited by 9
  8. 2024Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailabilitycited by 9
  9. 2023Delay Sensitive Hierarchical Federated Learning with Stochastic Local Updatescited by 8
  10. 2024Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysiscited by 8
  11. 2023Towards Bias Correction of FedAvg over Nonuniform and Time-Varying Communicationscited by 6
  12. 2023Distributed Personalized Empirical Risk Minimizationcited by 6
33 more
  1. 2025Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainablecited by 6
  2. 2023Federated Learning in the Presence of Adversarial Client Unavailabilitycited by 5
  3. 2024FedStale: leveraging stale client updates in federated learningcited by 5
  4. 2024DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networkscited by 5
  5. 2024Federated brain tumor segmentation: an extensive benchmarkcited by 5
  6. 2024Riemannian Federated Learning via Averaging Gradient Streamscited by 4
  7. 2024Empowering Federated Learning with Implicit Gossiping: Mitigating Connection Unreliability Amidst Unknown and Arbitrary Dynamicscited by 3
  8. 2024Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participationcited by 3
  9. 2024Distributed Online Optimization with Stochastic Agent Availabilitycited by 3
  10. 2024Asynchronous Federated Learning: A Scalable Approach for Decentralized Machine Learningcited by 3
  11. 2025Bant: Byzantine Antidote via Trial Function and Trust Scorescited by 3
  12. 2025Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participationcited by 3
  13. 2023Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environmentscited by 2
  14. 2024How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learningcited by 2
  15. 2024SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustmentscited by 2
  16. 2024Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networkscited by 2
  17. 2024Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGDcited by 2
  18. 2025Generalization in Federated Learning: A Conditional Mutual Information Frameworkcited by 2
  19. 2023A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averagingcited by 1
  20. 2024Adaptive Federated Learning in Heterogeneous Wireless Networks with Independent Samplingcited by 1
  21. 2024Federated Learning and AI Regulation in the European Union: Who is Responsible? -- An Interdisciplinary Analysiscited by 1
  22. 2024Debiasing Federated Learning with Correlated Client Participationcited by 1
  23. 2024ProFL: Performative Robust Optimal Federated Learningcited by 1
  24. 2025Communication-Efficient Device Scheduling for Federated Learning Using Lyapunov Optimizationcited by 1
  25. 2025Deploying Large AI Models on Resource-Limited Devices with Split Federated Learningcited by 1
  26. 2024FedAR: Addressing Client Unavailability in Federated Learning with Local Update Approximation and Rectificationcited by 0
  27. 2025Cooperative SGD with Dynamic Mixing Matricescited by 0
  28. 2025FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learningcited by 0
  29. 2026Communication-Efficient Federated AUC Maximization with Cyclic Client Participationcited by 0
  30. 2026SA-PEF: Step-Ahead Partial Error Feedback for Efficient Federated Learningcited by 0
  31. 2026FedQueue: Queue-Aware Federated Learning for Cross-Facility HPC Trainingcited by 0
  32. 2026Experience Constrained Hierarchical Federated Reinforcement Learning for Large-scale UAV Teams in Hazardous Environmentscited by 0
  33. 2026Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networkscited by 0