mlsanityData to 14 Oct 2026

FedCGD: Collective Gradient Divergence Optimized Scheduling for Wireless Federated Learning

arXiv 2506.07581 ↗First posted 9 Jun 2025cs.LG cs.AI cs.DCcited by 2

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a promising paradigm for multiple devices to cooperatively train a model. When applied in wireless networks, two issues consistently affect the performance of FL, i.e., data heterogeneity of devices and limited bandwidth. Many papers have investigated device scheduling strategies considering the two issues. However, most of them recognize data heterogeneity as a property of individual devices. In this paper, we prove that the convergence speed of FL is affected by the sum of device-level and sample-level collective gradient divergence (CGD). The device-level CGD refers to the gradient divergence of the scheduled device group, instead of the sum of the individual device divergence. The sample-level CGD is statistically upper bounded by sampling variance, which is inversely proportional to the total number of samples scheduled for local update. To derive a tractable form of the device-level CGD, we further consider a classification problem and transform it into the weighted earth moving distance (WEMD) between the group distribution and the global distribution. Then we propose FedCGD algorithm to minimize the sum of multi-level CGDs by balancing WEMD and sampling variance, within polynomial time. Simulation shows that the proposed strategy increases classification accuracy on the CIFAR-10 dataset by up to 4.2% while scheduling 41.8% fewer devices, and flexibly switches between reducing WEMD and reducing sampling variance.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 64 references that are in the map. First posted on arXiv 9 Jun 2025.

Builds on

37 of 64 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  4. 2018Federated Learning with Non-IID Datacited by 1,108
  5. 2020Adaptive Federated Optimizationcited by 1,046
  6. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  7. 2019Federated Learning with Personalization Layerscited by 541
  8. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  9. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  10. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  11. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 243
  12. 2023FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learningcited by 149
25 more
  1. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  2. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 109
  3. 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 103
  4. 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
  5. 2020Convergence Time Optimization for Federated Learning over Wireless Networkscited by 81
  6. 2020Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edgecited by 71
  7. 2020Scheduling for Cellular Federated Edge Learning with Importance and Channel Awarenesscited by 62
  8. 2021FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learningcited by 43
  9. 2021Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraintscited by 36
  10. 2021Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networkscited by 35
  11. 2022Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reductioncited by 32
  12. 2023Why Batch Normalization Damage Federated Learning on Non-IID Data?cited by 29
  13. 2020Federated Learning and Wireless Communicationscited by 27
  14. 2019Data-Importance Aware User Scheduling for Communication-Efficient Edge Machine Learningcited by 20
  15. 2021Context-Aware Online Client Selection for Hierarchical Federated Learningcited by 20
  16. 2023Federated Learning for Data Streamscited by 16
  17. 2024Training Diffusion Models with Federated Learningcited by 15
  18. 2022Federated Learning with Flexible Controlcited by 12
  19. 2020Edge Learning with Timeliness Constraints: Challenges and Solutionscited by 11
  20. 2024Mobility Accelerates Learning: Convergence Analysis on Hierarchical Federated Learning in Vehicular Networkscited by 11
  21. 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learningcited by 9
  22. 2024Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networkscited by 9
  23. 2022MOB-FL: Mobility-Aware Federated Learning for Intelligent Connected Vehiclescited by 8
  24. 2023Asynchronous Wireless Federated Learning with Probabilistic Client Selectioncited by 4
  25. 2024Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025FedTeddi: Temporal Drift and Divergence Aware Scheduling for Timely Federated Edge Learningcited by 1
  2. 2026Sylvas: Synergistic Learning Value based Device Scheduling in Federated Continual Learningcited by 0