Towards Flexible Device Participation in Federated Learning
Not on the map. Why?
Abstract (arXiv)
Traditional federated learning algorithms impose strict requirements on the participation rates of devices, which limit the potential reach of federated learning. This paper extends the current learning paradigm to include devices that may become inactive, compute incomplete updates, and depart or arrive in the middle of training. We derive analytical results to illustrate how allowing more flexible device participation can affect the learning convergence when data is not independently and identically distributed (non-IID). We then propose a new federated aggregation scheme that converges even when devices may be inactive or return incomplete updates. We also study how the learning process can adapt to early departures or late arrivals, and analyze their impacts on the convergence.
Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 8; 2022: 15; 2023: 17; 2024: 11; 2025: 9; 2026: 4.
64 papers.
Sort:
- 2021Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applicationscited by 96
- 2021Fast Federated Learning in the Presence of Arbitrary Device Unavailabilitycited by 72
- 2022A Unified Analysis of Federated Learning with Arbitrary Client Participationcited by 45
- 2021Anarchic Federated Learningcited by 42
- 2022Federated Minimax Optimization: Improved Convergence Analyses and Algorithmscited by 37
- 2023On the Convergence of Federated Averaging with Cyclic Client Participationcited by 31
- 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
- 2021Resource-Efficient Federated Learningcited by 26
- 2023Topology-aware Federated Learning in Edge Computing: A Comprehensive Surveycited by 23
- 2022Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networkscited by 18
- 2022Anchor Sampling for Federated Learning with Partial Client Participationcited by 14
- 2023DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Datasetcited by 14
38 more
- 2023Federated Learning with Regularized Client Participationcited by 13
- 2022Towards Energy-Aware Federated Learning on Battery-Powered Clientscited by 11
- 2022Collaborative Training of Medical Artificial Intelligence Models with non-uniform Labelscited by 10
- 2023MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updatescited by 10
- 2023Over-the-Air Federated Learning and Optimizationcited by 10
- 2021Client Selection in Federated Learning based on Gradients Importancecited by 9
- 2024Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailabilitycited by 9
- 2022Federated Learning Using Variance Reduced Stochastic Gradient for Probabilistically Activated Agentscited by 8
- 2024Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysiscited by 8
- 2021FedFog: Network-Aware Optimization of Federated Learning over Wireless Fog-Cloud Systemscited by 6
- 2022Learnings from Federated Learning in the Real worldcited by 6
- 2022Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systemscited by 6
- 2023Towards Bias Correction of FedAvg over Nonuniform and Time-Varying Communicationscited by 6
- 2023Online Vertical Federated Learning for Cooperative Spectrum Sensingcited by 6
- 2021The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communicationcited by 5
- 2023Multi-Carrier NOMA-Empowered Wireless Federated Learning with Optimal Power and Bandwidth Allocationcited by 5
- 2023Federated Learning in the Presence of Adversarial Client Unavailabilitycited by 5
- 2024Decentralized Federated Learning Over Imperfect Communication Channelscited by 5
- 2022FedSS: Federated Learning with Smart Selection of clientscited by 4
- 2022Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networkscited by 4
- 2023Federated Learning Under Restricted User Availabilitycited by 4
- 2024Application of Machine Learning Optimization in Cloud Computing Resource Scheduling and Managementcited by 4
- 2021Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workerscited by 3
- 2022Combating Client Dropout in Federated Learning via Friend Model Substitutioncited by 3
- 2023Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updatescited by 3
- 2023Collaborative Policy Learning for Dynamic Scheduling Tasks in Cloud-Edge-Terminal IoT Networks Using Federated Reinforcement Learningcited by 3
- 2024Empowering Federated Learning with Implicit Gossiping: Mitigating Connection Unreliability Amidst Unknown and Arbitrary Dynamicscited by 3
- 2022Privacy Amplification via Random Participation in Federated Learningcited by 2
- 2022STSyn: Speeding Up Local SGD with Straggler-Tolerant Synchronizationcited by 2
- 2023First-Order Dynamic Optimization for Streaming Convex Costscited by 2
- 2023Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environmentscited by 2
- 2024Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networkscited by 2
- 2024Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learningcited by 2
- 2025Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directionscited by 2
- 2023A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averagingcited by 1
- 2024Federated Learning with Flexible Architecturescited by 1
- 2024Seamless Integration: Sampling Strategies in Federated Learning Systemscited by 1
- 2024Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Designcited by 1
50 most cited of 64 All 64 (JSON)
- 2026FedeRage: Provably Convergent Agnostic Federated Learning under General Client Drift17 Sep 2026
- 2026FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching8 Jun 2026
- 2026Revealing the influence of participant failures on model quality in cross-silo Federated Learning26 Mar 2026
- 2026Communication-Efficient Federated AUC Maximization with Cyclic Client Participation4 Jan 2026
- 2025Closing the Generalization Gap in Parameter-efficient Federated Edge Learning28 Nov 2025
- 2025Dynamic Participation in Federated Learning: Benchmarks and a Knowledge Pool Plugin20 Nov 2025
- 2025FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes12 Oct 2025
- 2025Cooperative SGD with Dynamic Mixing Matrices20 Aug 2025
- 2025RIFLES: Resource-effIcient Federated LEarning via Scheduling19 May 2025
- 2025TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction24 Apr 2025
- 2025Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directions17 Apr 2025
- 2025Unifying Physics- and Data-Driven Modeling via Novel Causal Spatiotemporal Graph Neural Network for Interpretable Epidemic Forecasting7 Apr 2025
38 more
- 2025Communication-Efficient Device Scheduling for Federated Learning Using Lyapunov Optimization1 Mar 2025
- 2024Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning18 Dec 2024
- 2024Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis30 Oct 2024
- 2024Communication-Efficient Federated Learning under Dynamic Device Arrival and Departure: Convergence Analysis and Algorithm Design8 Oct 2024
- 2024Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability26 Sep 2024
- 2024Seamless Integration: Sampling Strategies in Federated Learning Systems18 Aug 2024
- 2024Federated Learning with Flexible Architectures14 Jun 2024
- 2024Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networks6 Jun 2024
- 2024Decentralized Federated Learning Over Imperfect Communication Channels21 May 2024
- 2024Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations11 May 2024
- 2024Empowering Federated Learning with Implicit Gossiping: Mitigating Connection Unreliability Amidst Unknown and Arbitrary Dynamics15 Apr 2024
- 2024Application of Machine Learning Optimization in Cloud Computing Resource Scheduling and Management27 Feb 2024
- 2023Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environments27 Dec 2023
- 2023Online Vertical Federated Learning for Cooperative Spectrum Sensing18 Dec 2023
- 2023DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset20 Oct 2023
- 2023Over-the-Air Federated Learning and Optimization16 Oct 2023
- 2023First-Order Dynamic Optimization for Streaming Convex Costs11 Oct 2023
- 2023Federated Learning Under Restricted User Availability25 Sep 2023
- 2023Collaborative Policy Learning for Dynamic Scheduling Tasks in Cloud-Edge-Terminal IoT Networks Using Federated Reinforcement Learning2 Jul 2023
- 2023MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updates21 Jun 2023
- 2023Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates11 Jun 2023
- 2023A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging6 Jun 2023
- 2023Towards Bias Correction of FedAvg over Nonuniform and Time-Varying Communications1 Jun 2023
- 2023Federated Learning in the Presence of Adversarial Client Unavailability31 May 2023
- 2023Addressing Class Variable Imbalance in Federated Semi-supervised Learning21 Mar 2023
- 2023Multi-Carrier NOMA-Empowered Wireless Federated Learning with Optimal Power and Bandwidth Allocation13 Feb 2023
- 2023Federated Learning with Regularized Client Participation7 Feb 2023
- 2023On the Convergence of Federated Averaging with Cyclic Client Participation6 Feb 2023
- 2023Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey6 Feb 2023
- 2022Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networks5 Dec 2022
- 2022Collaborative Training of Medical Artificial Intelligence Models with non-uniform Labels24 Nov 2022
- 2022Federated Learning Using Variance Reduced Stochastic Gradient for Probabilistically Activated Agents25 Oct 2022
- 2022STSyn: Speeding Up Local SGD with Straggler-Tolerant Synchronization6 Oct 2022
- 2022Towards Energy-Aware Federated Learning on Battery-Powered Clients9 Aug 2022
- 2022FedSS: Federated Learning with Smart Selection of clients10 Jul 2022
- 2022Anchor Sampling for Federated Learning with Partial Client Participation13 Jun 2022
- 2022A Unified Analysis of Federated Learning with Arbitrary Client Participation26 May 2022
- 2022Combating Client Dropout in Federated Learning via Friend Model Substitution26 May 2022
50 newest of 64 All 64 (JSON)
- 2021Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applicationscited by 96
- 2021Fast Federated Learning in the Presence of Arbitrary Device Unavailabilitycited by 72
- 2022A Unified Analysis of Federated Learning with Arbitrary Client Participationcited by 45
- 2021Anarchic Federated Learningcited by 42
- 2022Federated Minimax Optimization: Improved Convergence Analyses and Algorithmscited by 37
- 2023On the Convergence of Federated Averaging with Cyclic Client Participationcited by 31
- 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
- 2021Resource-Efficient Federated Learningcited by 26
- 2023Topology-aware Federated Learning in Edge Computing: A Comprehensive Surveycited by 23
- 2022Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networkscited by 18
- 2022Anchor Sampling for Federated Learning with Partial Client Participationcited by 14
- 2023DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Datasetcited by 14
12 most cited of 64 All 64 (JSON)
- 2026FedeRage: Provably Convergent Agnostic Federated Learning under General Client Drift17 Sep 2026
- 2026FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching8 Jun 2026
- 2026Revealing the influence of participant failures on model quality in cross-silo Federated Learning26 Mar 2026
- 2026Communication-Efficient Federated AUC Maximization with Cyclic Client Participation4 Jan 2026
- 2025Closing the Generalization Gap in Parameter-efficient Federated Edge Learning28 Nov 2025
- 2025Dynamic Participation in Federated Learning: Benchmarks and a Knowledge Pool Plugin20 Nov 2025
- 2025FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes12 Oct 2025
- 2025Cooperative SGD with Dynamic Mixing Matrices20 Aug 2025
- 2025RIFLES: Resource-effIcient Federated LEarning via Scheduling19 May 2025
- 2025TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction24 Apr 2025
- 2025Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directions17 Apr 2025
- 2025Unifying Physics- and Data-Driven Modeling via Novel Causal Spatiotemporal Graph Neural Network for Interpretable Epidemic Forecasting7 Apr 2025
12 newest of 64 All 64 (JSON)