Enhancing Decentralized Federated Learning With Model Pruning and Adaptive Communication

doi:10.1109/TII.2024.3424497

Enhancing Decentralized Federated Learning With Model Pruning and Adaptive Communication

2025-01-01

1

PRE

AI

DOI：10.1109/TII.2024.3424497

Original

Original request for help

Save

Abstract

En 中文

Federated learning (FL) is a distributed learning paradigm that enables large-scale IoT devices to collaboratively train a shared model while preserving the privacy of local data. To avoid the single-point-of-failure of the conventional parameter server architecture, the study concentrates on the decentralized FL (DFL) paradigm building on the device-to-device communication network. However, existing DFL frameworks encounter challenges related to resource limitations, privacy protection, and data heterogeneity. To overcome these challenges, the study proposes and implements DF2-MPC in industrial IoT, an efficient DFL framework with personalized model pruning and adaptive communication. Specifically, a personalized pruning ratio determination approach is designed by exploiting the model pruning technique. This approach enables all devices to flexibly determine pruning ratios by themselves, thereby achieving both communication savings and privacy protection. Then, this study designs an adaptive neighbor selection scheme, which can enhance model performance and foster model consensus under resource constraints. In addition, the study theoretically proves the convergence performance of DF2-MPC. Finally, extensive simulations on three real-world traces are conducted to corroborate the superiority of DF2-MPC, demonstrating that the method can improve communication efficiency with satisfactory model accuracy and convergence performance.

Keywords:

Adaptation models

Performance evaluation

Privacy

Computational modeling

Training

Device-to-device communication

Data models

Communication efficiency

decentralized federated learning (DFL)

industrial Internet of Things (IoT)

model pruning

neighbor selection

Enhancing Decentralized Federated Learning With Model Pruning and Adaptive Communication

Abstract

Journal

Organization