Joint Model Pruning and Resource Allocation for Wireless Time-triggered Federated Learning

TY - CONF

T1 - Joint Model Pruning and Resource Allocation for Wireless Time-triggered Federated Learning

AU - Zhang, Xinlu

AU - Deng, Yansha

AU - Mahmoodi, Toktam

N1 - Publisher Copyright: © 2024 IEEE.

PY - 2024

Y1 - 2024

N2 - 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 l2-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.

AB - 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 l2-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.

KW - communication bottleneck

KW - convergence rate and learning latency

KW - federated learning

KW - Network pruning

UR - http://www.scopus.com/inward/record.url?scp=105000833249&partnerID=8YFLogxK

U2 - 10.1109/GLOBECOM52923.2024.10901166

DO - 10.1109/GLOBECOM52923.2024.10901166

M3 - Paper

AN - SCOPUS:105000833249

SP - 950

EP - 955

T2 - 2024 IEEE Global Communications Conference, GLOBECOM 2024

Y2 - 8 December 2024 through 12 December 2024

ER -