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

Changheng Wang; Xianchao Zhang; Zhiqing Wei; Lingzhu Zhao; Zhongming Yang; Zhiyong Feng

cs.DCSep 13, 2026

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

Authors: Changheng Wang, Xianchao Zhang, Zhiqing Wei, Lingzhu Zhao, Zhongming Yang, Zhiyong Feng

Organizations: Key Labora-tory of Universal Wireless Communications, Ministry of Education, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China · Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems, Jiaxing University, Jiaxing 314001, China · School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710000, China · School of Information Science and Engineering, Southeast University, Nanjing 210096, China

Abstract

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.

Figures & tables

Methodology	Core Mechanism	Limitation / Gap
Data Heterogeneity Solutions
Regularization [ 3 , 7 , 8 , 9 ]	Local objective constraint	Hyperparameter sensitivity
Clustered FL [ 10 , 11 , 12 , 13 ]	Similarity-based grouping	Cold-start & high overhead
Meta-learning [ 14 , 15 , 16 ]	Few-shot adaptability	Hessian-based complexity
SFL [ 17 ]	Centralized-Fed hybrid	Paradigm-specific tuning
Data-centric [ 18 , 19 , 20 ]	Distribution alignment	Privacy & bias concerns

TABLE I: Technical Comparison of Related Methodologies.

Fig. 1: Illustration of the FedRW structure over a reliable wireless network with $M=3$ RW chains and $Q=3$ clients per chain.

Wireless Parameters		Algorithmic Parameters
Parameter	Value	Parameter	Value
$B$	10 MHz	$U$	100
$P$	23 dBm	$M$	5
$N_{0}$	$-$ 174 $\mathrm{dBm/Hz}$	$Q$	3
$\epsilon$	1e-5	Batch size	64
$\gamma_{\tau}$	20 ms	$\lambda$	0.01

TABLE II: Simulation Parameters

Panel of Figure 4 — Fig. 2: MNIST classification accuracy vs. total communication overhead under Non-IID data distribution (200 rounds).

Panel of Figure 5 — Fig. 3: Classification accuracy and training loss on Fashion-MNIST, CIFAR-10, and CIFAR-100 in mixed Non-IID settings.

Fig. 4: MNIST classification accuracy of FedRW in Dirichlet Non-IID (

\zeta_{d}

=0.1) setting with varying random walk chain counts and lengths.

Panel of Figure 7 — Fig. 5: Performance comparison between FedRW and state-of-the-art baselines in Dirichlet Non-IID setting.

Panel of Figure 8 — Fig. 6: Performance comparison of FedRW under varying degrees of intra-chain data diversity.

Panel of Figure 9 — Fig. 7: Comparison between unweighted and weighted aggregation schemes.

Panel of Figure 10 — Fig. 8: Comparative of classification accuracy and loss between the proposed joint RW path selection and transmission parameter optimization algorithm and baselines on MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100.

Panel of Figure 11 — Fig. 9: Comparison of classification accuracy between the proposed algorithm and its variant with constraint ( c ) relaxed.

Panel of Figure 12 — Fig. 10: Comparison of number of aggregated RW chains under different network conditions on MNIST in mixed Non-IID ( $\zeta_{n}$ =0) setting.

Federated Learning

Federated learning trains shared models across data holders without requiring them to pool their raw data.

See all 951 papers

Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks
Mar 16, 2026Xiaoyu He, Weicai Li, Tiejun Lv +1Federated Learning Communication-Efficient Distributed Training
School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China · Center for Target Cognition Information Processing Science and Technology, and the Key Laboratory of Modern Measurement and Control Technology, Ministry of Education, both at Beijing Information Science and Technology University, Beijing, China
FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks
Aug 7, 2026Majid Kundroo, Tinku Singh, Taehong KimFederated Learning Aggregation Wireless Local Area Networks
aSchool of Information and Communication Engineering, Chungbuk National University, Cheongju, 28644, Republic of Korea · bSchool of Computer Science Engineering and Technology, Bennett University, Greater Noida, 201310, India
Federated Learning with Hypergradient-based Online Update of Aggregation Weights
May 1, 2026Ayano Nakai-Kasai, Tadashi WadayamaFederated Learning Aggregation Hypergradient Optimization
Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya, Aichi 466-8555, Japan

Mar 16, 2026J/K move · Enter open · S save

Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks

Xiaoyu He, Weicai Li, Tiejun Lv, Xi Yu

School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China · Center for Target Cognition Information Processing Science and Technology, and the Key Laboratory of Modern Measurement and Control Technology, Ministry of Education, both at Beijing Information Science and Technology University, Beijing, China

Federated Learning Communication-Efficient Distributed Training Wireless Communications Neural Network Pruning

Open paper AskPDF arXiv

Decentralized federated learning (D-FL) enables privacy-preserving training without a central server, but multi-hop model exchanges and aggregation are often bottlenecked by communication resource constraints. To address this issue, we propose a joint routing-and-pruning framework that optimizes routing paths and pruning rates to maintain communication latency within prescribed limits. We analyze how the sum of model biases across all clients affects the convergence bound of D-FL and formulate an optimization problem that maximizes the model retention rate to minimize these biases under communication constraints. Further analysis reveals that each client's model retention rate is path-dependent, which reduces the original problem to a routing optimization. Leveraging this insight, we develop a routing algorithm that selects latency-efficient transmission paths, allowing more parameters to be delivered within the time budget and thereby improving D-FL convergence. Simulations demonstrate that, compared with unpruned systems, the proposed framework reduces average transmission latency by 27.8% and improves testing accuracy by approximately 12%. Furthermore, relative to standard benchmark routing algorithms, the proposed routing method improves accuracy by roughly 8%.

Abstract

Federated Learning

Explore similar work

Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks

FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks

Federated Learning with Hypergradient-based Online Update of Aggregation Weights