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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Xiaoyu, Li, Weicai, Lv, Tiejun, Yu, Xi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910054638157824
author He, Xiaoyu
Li, Weicai
Lv, Tiejun
Yu, Xi
author_facet He, Xiaoyu
Li, Weicai
Lv, Tiejun
Yu, Xi
contents 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%.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15188
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks
He, Xiaoyu
Li, Weicai
Lv, Tiejun
Yu, Xi
Machine Learning
Networking and Internet Architecture
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%.
title Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks
topic Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2603.15188