mlsanityData to 7 Oct 2026

Communication-Efficient Federated Learning via Optimal Client Sampling

arXiv 2007.15197 ↗First posted 30 Jul 2020cs.LG stat.MLcited by 39

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) ameliorates privacy concerns in settings where a central server coordinates learning from data distributed across many clients. The clients train locally and communicate the models they learn to the server; aggregation of local models requires frequent communication of large amounts of information between the clients and the central server. We propose a novel, simple and efficient way of updating the central model in communication-constrained settings based on collecting models from clients with informative updates and estimating local updates that were not communicated. In particular, modeling the progression of model's weights by an Ornstein-Uhlenbeck process allows us to derive an optimal sampling strategy for selecting a subset of clients with significant weight updates. The central server collects updated local models from only the selected clients and combines them with estimated model updates of the clients that were not selected for communication. We test this policy on a synthetic dataset for logistic regression and two FL benchmarks, namely, a classification task on EMNIST and a realistic language modeling task using the Shakespeare dataset. The results demonstrate that the proposed framework provides significant reduction in communication while maintaining competitive or achieving superior performance compared to a baseline. Our method represents a new line of strategies for communication-efficient FL that is orthogonal to the existing user-local methods such as quantization or sparsification, thus complementing rather than aiming to replace those existing methods.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 8; 2023: 8; 2024: 9; 2025: 4; 2026: 2.

39 papers.

Sort:

  1. 2021On Large-Cohort Training for Federated Learningcited by 73
  2. 2021Towards Fairness-Aware Federated Learningcited by 57
  3. 2022FedAvg with Fine Tuning: Local Updates Lead to Representation Learningcited by 55
  4. 2021Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Bettercited by 54
  5. 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 38
  6. 2022Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reductioncited by 32
  7. 2021Local Adaptivity in Federated Learning: Convergence and Consistencycited by 31
  8. 2022Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraintscited by 30
  9. 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
  10. 2022DELTA: Diverse Client Sampling for Fasting Federated Learningcited by 24
  11. 2023On the Role of Server Momentum in Federated Learningcited by 16
  12. 2024FedImpro: Measuring and Improving Client Update in Federated Learningcited by 15
27 more
  1. 2023Federated Learning with Regularized Client Participationcited by 13
  2. 2024Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimizationcited by 12
  3. 2023Async-HFL: Efficient and Robust Asynchronous Federated Learning in Hierarchical IoT Networkscited by 11
  4. 2021Client Selection in Federated Learning based on Gradients Importancecited by 9
  5. 2021Sparsified Secure Aggregation for Privacy-Preserving Federated Learningcited by 8
  6. 2021Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedbackcited by 6
  7. 2023A Comprehensive Survey On Client Selections in Federated Learningcited by 6
  8. 2024Influence-Oriented Personalized Federated Learningcited by 6
  9. 2023Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networkscited by 5
  10. 2022Multi-Model Federated Learningcited by 4
  11. 2022Combating Client Dropout in Federated Learning via Friend Model Substitutioncited by 3
  12. 2023Network Adaptive Federated Learning: Congestion and Lossy Compressioncited by 3
  13. 2023Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learningcited by 2
  14. 2024Election of Collaborators via Reinforcement Learning for Federated Brain Tumor Segmentationcited by 2
  15. 2024Federated Learning Can Find Friends That Are Advantageouscited by 1
  16. 2024Federated Learning with Flexible Architecturescited by 1
  17. 2024FLMarket: Enabling Privacy-preserved Pre-training Data Pricing for Federated Learningcited by 1
  18. 2025A Two-Stage CAE-Based Federated Learning Framework for Efficient Jamming Detection in 5G Networkscited by 1
  19. 2025Communication-Efficient Device Scheduling for Federated Learning Using Lyapunov Optimizationcited by 1
  20. 2025Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacycited by 1
  21. 2025Tackling Data Heterogeneity in Federated Learning through Knowledge Distillation with Inequitable Aggregationcited by 1
  22. 2022Deep Unfolding-based Weighted Averaging for Federated Learning in Heterogeneous Environmentscited by 0
  23. 2023When to Trust Aggregated Gradients: Addressing Negative Client Sampling in Federated Learningcited by 0
  24. 2024FedEGG: Federated Learning with Explicit Global Guidancecited by 0
  25. 2024Age-of-Gradient Updates for Federated Learning over Random Access Channelscited by 0
  26. 2026Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulationcited by 0
  27. 2026Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learningcited by 0