mlsanityData to 14 Oct 2026

Learning to Sync at the Edge: Client-Side Adaptive Synchronization for Federated Learning

arXiv 2610.14268 ↗First posted 9 Oct 2026cs.DC cs.LG cs.NIcited by 0

Not on the map. Why?

Abstract (arXiv)

The scalability and performance of edge federated learning are fundamentally constrained by synchronization bottlenecks. Clients operate under heterogeneous compute, time-varying communication conditions, and, in some settings, privacy constraints, yet synchronization is often still handled with fixed schedules. However, synchronization decisions are often made outside the client, even though the client directly observes local progress, resource state, and communication conditions. We present a client-side reinforcement learning synchronization framework in which each client decides during training whether to upload, download, synchronize bidirectionally, or defer communication. The framework places a lightweight scheduler alongside the local model and formulates synchronization as a resource-aware control problem driven by local learning and system state. We study this framework on two representative edge workloads, spatiotemporal traffic forecasting and image classification. Across both settings, adaptive client-side synchronization improves the accuracy-cost trade-off, reducing system cost in traffic forecasting while maintaining competitive cost and improving final accuracy in image classification. We also consider privacy-constrained settings, where synchronization must account for not only latency and energy but also privacy expenditure. Overall, our results show that synchronization in edge federated learning is better treated as an adaptive client-side control problem than only as a server-side coordination mechanism.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 35 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

15 of 35 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  6. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  7. 2019Towards Federated Learning at Scale: System Designcited by 832
  8. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  9. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
  10. 2019Asynchronous Federated Optimizationcited by 267
  11. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  12. 2020Privacy-preserving Traffic Flow Prediction: A Federated Learning Approachcited by 83
3 more
  1. 2020Towards Flexible Device Participation in Federated Learningcited by 65
  2. 2022A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learningcited by 31
  3. 2024REFOL: Resource-Efficient Federated Online Learning for Traffic Flow Forecastingcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Joint Optimization of Training and Inference in Federated Edge Learning via Constrained Multi-Objective Deep Reinforcement Learning
  2. 2021Federated Ensemble Model-based Reinforcement Learning in Edge Computing
  3. 2026Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learning
  4. 2026Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention
  5. 2026AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments
  6. 2025FAuNO: Semi-Asynchronous Federated Reinforcement Learning Framework for Task Offloading in Edge Systems
  7. 2026FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices
  8. 2026Task-oriented Framework for Communication-Efficient Federated Learning: From Isolated Optimization to Holistic Synergy