Saved in:
Bibliographic Details
Main Authors: Zhang, Xinlu, Deng, Yansha, Mahmoodi, Toktam
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.01765
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908354891218944
author Zhang, Xinlu
Deng, Yansha
Mahmoodi, Toktam
author_facet Zhang, Xinlu
Deng, Yansha
Mahmoodi, Toktam
contents Time-triggered federated learning, in contrast to conventional event-based federated learning, organizes users into tiers based on fixed time intervals. However, this network still faces challenges due to a growing number of devices and limited wireless bandwidth, increasing issues like stragglers and communication overhead. In this paper, we apply model pruning to wireless Time-triggered systems and jointly study the problem of optimizing the pruning ratio and bandwidth allocation to minimize training loss under communication latency constraints. To solve this joint optimization problem, we perform a convergence analysis on the gradient $l_2$-norm of the asynchronous multi-tier federated learning (FL) model with adaptive model pruning. The convergence upper bound is derived and a joint optimization problem of pruning ratio and wireless bandwidth is defined to minimize the model training loss under a given communication latency constraint. The closed-form solutions for wireless bandwidth and pruning ratio by using KKT conditions are then formulated. As indicated in the simulation experiments, our proposed TT-Prune demonstrates a 40% reduction in communication cost, compared with the asynchronous multi-tier FL without model pruning, while maintaining the model convergence at the same level.
format Preprint
id arxiv_https___arxiv_org_abs_2408_01765
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Joint Model Pruning and Resource Allocation for Wireless Time-triggered Federated Learning
Zhang, Xinlu
Deng, Yansha
Mahmoodi, Toktam
Machine Learning
Information Theory
Time-triggered federated learning, in contrast to conventional event-based federated learning, organizes users into tiers based on fixed time intervals. However, this network still faces challenges due to a growing number of devices and limited wireless bandwidth, increasing issues like stragglers and communication overhead. In this paper, we apply model pruning to wireless Time-triggered systems and jointly study the problem of optimizing the pruning ratio and bandwidth allocation to minimize training loss under communication latency constraints. To solve this joint optimization problem, we perform a convergence analysis on the gradient $l_2$-norm of the asynchronous multi-tier federated learning (FL) model with adaptive model pruning. The convergence upper bound is derived and a joint optimization problem of pruning ratio and wireless bandwidth is defined to minimize the model training loss under a given communication latency constraint. The closed-form solutions for wireless bandwidth and pruning ratio by using KKT conditions are then formulated. As indicated in the simulation experiments, our proposed TT-Prune demonstrates a 40% reduction in communication cost, compared with the asynchronous multi-tier FL without model pruning, while maintaining the model convergence at the same level.
title Joint Model Pruning and Resource Allocation for Wireless Time-triggered Federated Learning
topic Machine Learning
Information Theory
url https://arxiv.org/abs/2408.01765