mlsanityData to 14 Oct 2026

Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data

arXiv 2609.14246 ↗First posted 13 Sep 2026cs.DC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In wireless federated learning (FL), data heterogeneity and multiple local updates induce client drift, degrading model convergence. It is further affected by unreliable wireless links, as transmission errors may invalidate model updates. To address these challenges, we propose a federated random walk averaging (FedRW) framework, which is a variant of federated averaging (FedAvg) that mitigates data heterogeneity by updating models along random walk (RW) paths and aggregating them at the server. Model parameters are transmitted in packets with retransmission support to improve training quality by mitigating wireless errors along RW paths. Meanwhile, wireless transmission delays hinder the exploration of FedRW. To this end, we formulate a joint optimization problem that integrates learning, RW path selection, and transmission parameter tuning, aiming to minimize the training loss under delay constraints. By deriving an upper bound on the expected convergence of FedRW over unreliable wireless networks, we reduce the problem to a general form agnostic to task type and model architecture. A distributed solution is then proposed, in which the server or clients optimize packet size and maximum number of retransmissions locally, and efficiently select reliable and expandable next-hop nodes via a resilience-aware beam search with dynamic pruning. Simulation results show that FedRW achieves 2.26%-9% higher accuracy than state-of-the-art baselines under high data heterogeneity. Furthermore, the jointly optimized FedRW yields at least 2.78% higher accuracy and faster convergence compared to baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 53 references that are in the map. First posted on arXiv 13 Sep 2026.

Builds on

38 of 53 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
  6. 2020Adaptive Federated Optimizationcited by 1,046
  7. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  8. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 539
  9. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  10. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  11. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
  12. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
26 more
  1. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  2. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  3. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
  4. 2021Decentralized Federated Averagingcited by 114
  5. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  6. 2020Convergence Time Optimization for Federated Learning over Wireless Networkscited by 81
  7. 2020Fast-Convergent Federated Learningcited by 61
  8. 2020The Global Landscape of Neural Networks: An Overviewcited by 57
  9. 2020FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measurecited by 46
  10. 2023Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscapecited by 46
  11. 2020Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learningcited by 24
  12. 2022Walk for Learning: A Random Walk Approach for Federated Learning from Heterogeneous Datacited by 19
  13. 2021Integrating Over-the-Air Federated Learning and Non-Orthogonal Multiple Access: What Role can RIS Play?cited by 14
  14. 2023Feature Matching Data Synthesis for Non-IID Federated Learningcited by 13
  15. 2022Federated Learning and Meta Learning: Approaches, Applications, and Directionscited by 12
  16. 2022FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacycited by 9
  17. 2020Federated Learning in Multi-RIS Aided Systemscited by 7
  18. 2021A Dispersed Federated Learning Framework for 6G-Enabled Autonomous Driving Carscited by 6
  19. 2023OFDMA-F2L: Federated Learning With Flexible Aggregation Over an OFDMA Air Interfacecited by 6
  20. 2019Decentralized Consensus Optimization Based on Parallel Random Walkcited by 5
  21. 2022Towards Communication-Learning Trade-off for Federated Learning at the Network Edgecited by 5
  22. 2020Wireless Feedback Control with Variable Packet Length for Industrial IoTcited by 4
  23. 2020Wireless Distributed Edge Learning: How Many Edge Devices Do We Need?cited by 3
  24. 2022Rate-Convergence Tradeoff of Federated Learning over Wireless Channelcited by 2
  25. 2015Channel-Adaptive Packetization Policy for Minimal Latency and Maximal Energy Efficiencycited by 1
  26. 2025Decentralized Federated Averaging via Random Walkcited by 1

Built on by

Not cited yet.