mlsanityData to 14 Oct 2026

Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints

arXiv 2205.06730 ↗First posted 13 May 2022cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Federated learning systems facilitate training of global models in settings where potentially heterogeneous data is distributed across a large number of clients. Such systems operate in settings with intermittent client availability and/or time-varying communication constraints. As a result, the global models trained by federated learning systems may be biased towards clients with higher availability. We propose F3AST, an unbiased algorithm that dynamically learns an availability-dependent client selection strategy which asymptotically minimizes the impact of client-sampling variance on the global model convergence, enhancing performance of federated learning. The proposed algorithm is tested in a variety of settings for intermittently available clients under communication constraints, and its efficacy demonstrated on synthetic data and realistically federated benchmarking experiments using CIFAR100 and Shakespeare datasets. We show up to 186% and 8% accuracy improvements over FedAvg, and 8% and 7% over FedAdam on CIFAR100 and Shakespeare, respectively.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 35 of its 55 references that are in the map. First posted on arXiv 13 May 2022.

Builds on

35 of 55 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2018Group Normalizationcited by 1,524
  7. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  8. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  9. 2020Adaptive Federated Optimizationcited by 1,046
  10. 2019Towards Federated Learning at Scale: System Designcited by 832
  11. 2017Federated Multi-Task Learningcited by 672
  12. 2018Local SGD Converges Fast and Communicates Littlecited by 605
23 more
  1. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  2. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  3. 2019Agnostic Federated Learningcited by 456
  4. 2018Sparsified SGD with Memorycited by 376
  5. 2021A Field Guide to Federated Optimizationcited by 315
  6. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 305
  7. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 204
  8. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
  9. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  10. 2016Distributed Mean Estimation with Limited Communicationcited by 136
  11. 2013Communication Efficient Distributed Optimization using an Approximate Newton-type Methodcited by 132
  12. 2019DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compressioncited by 99
  13. 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 96
  14. 2014Stochastic Optimization with Importance Samplingcited by 91
  15. 2019Natural Compression for Distributed Deep Learningcited by 90
  16. 2021On Large-Cohort Training for Federated Learningcited by 74
  17. 2020Multi-Armed Bandit Based Client Scheduling for Federated Learningcited by 57
  18. 2019Semi-Cyclic Stochastic Gradient Descentcited by 40
  19. 2016Randomized Distributed Mean Estimation: Accuracy vs Communicationcited by 39
  20. 2020Communication-Efficient Federated Learning via Optimal Client Samplingcited by 39
  21. 2020Federated Learning under Importance Samplingcited by 26
  22. 2020Quantized Decentralized Stochastic Learning over Directed Graphscited by 24
  23. 2019SPARQ-SGD: Event-Triggered and Compressed Communication in Decentralized Stochastic Optimizationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 11; 2025: 6; 2026: 7.

30 papers.

Sort:

By area:

  1. 2022Client Selection in Federated Learning: Principles, Challenges, and Opportunitiescited by 62
  2. 2023Federated Learning under Heterogeneous and Correlated Client Availabilitycited by 18
  3. 2024Advances in Robust Federated Learning: A Survey with Heterogeneity Considerationscited by 12
  4. 2024Green Federated Learning: A new era of Green Aware AIcited by 12
  5. 2022FedGS: Federated Graph-based Sampling with Arbitrary Client Availabilitycited by 10
  6. 2023MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updatescited by 10
  7. 2024Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailabilitycited by 9
  8. 2024Communication-Efficient Federated Learning for LEO Satellite Networks Integrated with HAPs Using Hybrid NOMA-OFDMcited by 6
  9. 2024FedStale: leveraging stale client updates in federated learningcited by 5
  10. 2023Federated Learning Under Restricted User Availabilitycited by 4
  11. 2024Riemannian Federated Learning via Averaging Gradient Streamscited by 4
  12. 2023Collaborative Policy Learning for Dynamic Scheduling Tasks in Cloud-Edge-Terminal IoT Networks Using Federated Reinforcement Learningcited by 3
18 more
  1. 2024Empowering Federated Learning with Implicit Gossiping: Mitigating Connection Unreliability Amidst Unknown and Arbitrary Dynamicscited by 3
  2. 2025Analyzing the Impact of Participant Failures in Cross-Silo Federated Learningcited by 2
  3. 2024On-Demand Model and Client Deployment in Federated Learning with Deep Reinforcement Learningcited by 1
  4. 2024Debiasing Federated Learning with Correlated Client Participationcited by 1
  5. 2024Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Designcited by 1
  6. 2025FedAVOT: Exact Distribution Alignment in Federated Learning via Masked Optimal Transportcited by 1
  7. 2024Towards Fairness in Provably Communication-Efficient Federated Recommender Systemscited by 0
  8. 2025RIFLES: Resource-effIcient Federated LEarning via Schedulingcited by 0
  9. 2025Communication-Efficient Federated Learning with Adaptive Number of Participantscited by 0
  10. 2025Semi-decentralized Federated Time Series Prediction with Client Availability Budgetscited by 0
  11. 2025Computation-aware Energy-harvesting Federated Learning with Pipelined Cyclic Schedulingcited by 0
  12. 2026RefProtoFL: Communication-Efficient Federated Learning via External-Referenced Prototype Alignmentcited by 0
  13. 2026Revealing the influence of participant failures on model quality in cross-silo Federated Learningcited by 0
  14. 2026Robust Synchronisation for Federated Learning in The Face of Correlated Device Failurecited by 0
  15. 2026FedQueue: Queue-Aware Federated Learning for Cross-Facility HPC Trainingcited by 0
  16. 2026Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attentioncited by 0
  17. 2026FedeRage: Provably Convergent Agnostic Federated Learning under General Client Driftcited by 0
  18. 2026Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networkscited by 0