mlsanityData to 14 Oct 2026

Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge

arXiv 1804.08333 ↗First posted 23 Apr 2018cs.NI cs.LGcited by 352

Not on the map. Why?

Abstract (arXiv)

We envision a mobile edge computing (MEC) framework for machine learning (ML) technologies, which leverages distributed client data and computation resources for training high-performance ML models while preserving client privacy. Toward this future goal, this work aims to extend Federated Learning (FL), a decentralized learning framework that enables privacy-preserving training of models, to work with heterogeneous clients in a practical cellular network. The FL protocol iteratively asks random clients to download a trainable model from a server, update it with own data, and upload the updated model to the server, while asking the server to aggregate multiple client updates to further improve the model. While clients in this protocol are free from disclosing own private data, the overall training process can become inefficient when some clients are with limited computational resources (i.e. requiring longer update time) or under poor wireless channel conditions (longer upload time). Our new FL protocol, which we refer to as FedCS, mitigates this problem and performs FL efficiently while actively managing clients based on their resource conditions. Specifically, FedCS solves a client selection problem with resource constraints, which allows the server to aggregate as many client updates as possible and to accelerate performance improvement in ML models. We conducted an experimental evaluation using publicly-available large-scale image datasets to train deep neural networks on MEC environment simulations. The experimental results show that FedCS is able to complete its training process in a significantly shorter time compared to the original FL protocol.

Key facts. Cited by 352 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 86; 2022: 62; 2023: 69; 2024: 59; 2025: 55; 2026: 21.

352 papers.

Sort:

By area:

  1. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  2. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
  3. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  4. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  5. 2021Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learningcited by 93
  6. 2023Deep Model Fusion: A Surveycited by 91
  7. 2021Federated Reinforcement Learning: Techniques, Applications, and Open Challengescited by 81
  8. 2021On Large-Cohort Training for Federated Learningcited by 74
  9. 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
  10. 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
  11. 2022Client Selection in Federated Learning: Principles, Challenges, and Opportunitiescited by 62
  12. 2021Towards Fairness-Aware Federated Learningcited by 58
38 more
  1. 2021EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learningcited by 55
  2. 2022Communication-Efficient Adaptive Federated Learningcited by 55
  3. 2021Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysiscited by 51
  4. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  5. 2022A Survey on Heterogeneous Federated Learningcited by 42
  6. 2021Communication Efficiency in Federated Learning: Achievements and Challengescited by 40
  7. 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
  8. 2023Federated Learning for Connected and Automated Vehicles: A Survey of Existing Approaches and Challengescited by 40
  9. 2021Node Selection Toward Faster Convergence for Federated Learning on Non-IID Datacited by 39
  10. 2021A Comprehensive Survey of Incentive Mechanism for Federated Learningcited by 38
  11. 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
  12. 2022Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reductioncited by 32
  13. 2021FedZKT: Zero-Shot Knowledge Transfer towards Resource-Constrained Federated Learning with Heterogeneous On-Device Modelscited by 31
  14. 2022A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learningcited by 31
  15. 2021Federated Neural Collaborative Filteringcited by 30
  16. 2021Fusion of Federated Learning and Industrial Internet of Things: A Surveycited by 29
  17. 2021Efficient Device Scheduling with Multi-Job Federated Learningcited by 29
  18. 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
  19. 2021FEDZIP: A Compression Framework for Communication-Efficient Federated Learningcited by 27
  20. 2021Resource-Efficient Federated Learningcited by 26
  21. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  22. 2023FwdLLM: Efficient FedLLM using Forward Gradientcited by 26
  23. 2021Cost-Effective Federated Learning in Mobile Edge Networkscited by 25
  24. 2022Data Heterogeneity-Robust Federated Learning via Group Client Selection in Industrial IoTcited by 25
  25. 2022FedAdapter: Efficient Federated Learning for Modern NLPcited by 25
  26. 2022A Survey on Federated Recommendation Systemscited by 25
  27. 2023Green Edge AI: A Contemporary Surveycited by 25
  28. 2021Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learningcited by 23
  29. 2021Improving Fairness for Data Valuation in Horizontal Federated Learningcited by 22
  30. 2021Context-Aware Online Client Selection for Hierarchical Federated Learningcited by 20
  31. 2022FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneitycited by 20
  32. 2022Multi-Job Intelligent Scheduling with Cross-Device Federated Learningcited by 20
  33. 2023Towards Quantum Federated Learningcited by 20
  34. 2024Advances in APPFL: A Comprehensive and Extensible Federated Learning Frameworkcited by 19
  35. 2021Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligencecited by 18
  36. 2022The Cost of Training Machine Learning Models over Distributed Data Sourcescited by 18
  37. 2021FedH2L: Federated Learning with Model and Statistical Heterogeneitycited by 17
  38. 2022A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updatescited by 17

50 most cited of 352 All 352 (JSON)