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

TL;DR

This paper introduces a joint routing and pruning framework for decentralized federated learning in multi-hop wireless networks, optimizing communication efficiency and model accuracy under bandwidth constraints.

Contribution

It proposes a novel routing-and-pruning method that enhances D-FL performance by optimizing transmission paths and model retention rates within communication limits.

Findings

Reduces average transmission latency by 27.8%.

Improves testing accuracy by approximately 12%.

Enhances accuracy by roughly 8% over benchmark routing algorithms.

Abstract

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%.