TT-Prune: Joint Model Pruning and Resource Allocation for Communication-efficient Time-triggered Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) offers new opportunities in machine learning, particularly in addressing data privacy concerns. In contrast to conventional event-based federated learning, time-triggered federated learning (TT-Fed), as a general form of both asynchronous and synchronous FL, clusters users into different tiers based on fixed time intervals. However, the FL network consists of a growing number of user devices with limited wireless bandwidth, consequently magnifying issues such as stragglers and communication overhead. In this paper, we introduce adaptive model pruning to wireless TT-Fed systems and study the problem of jointly optimizing the pruning ratio and bandwidth allocation to minimize the training loss while ensuring minimal learning latency. To answer this question, we perform convergence analysis on the gradient l_2 norm of the TT-Fed model based on model pruning. Based on the obtained convergence upper bound, a joint optimization problem of pruning ratio and wireless bandwidth is formulated to minimize the model training loss under a given delay threshold. Then, we derive closed-form solutions for wireless bandwidth and pruning ratio using Karush-Kuhn-Tucker(KKT) conditions. The simulation results show that model pruning could reduce the communication cost by 40% while maintaining the model performance at the same level.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 39 references that are in the map. First posted on arXiv 6 Nov 2025.
Builds on
25 of 39 references.
References · 25
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2021Convex optimizationcited by 2,479
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
- 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
- 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 716
- 2019Importance Estimation for Neural Network Pruningcited by 531
- 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 475
- 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
- 2018Sparsified SGD with Memorycited by 373
- 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
- 2019Asynchronous Federated Optimizationcited by 264
- 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
13 more
- 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 219
- 2018Federated Learning via Over-the-Air Computationcited by 215
- 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
- 2019Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocationcited by 93
- 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
- 2020Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learningcited by 90
- 2020FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tierscited by 64
- 2021Federated Dropout -- A Simple Approach for Enabling Federated Learning on Resource Constrained Devicescited by 56
- 20196G Wireless Communication Systems: Applications, Requirements, Technologies, Challenges, and Research Directionscited by 34
- 2022Time-triggered Federated Learning over Wireless Networkscited by 10
- 2023Adaptive Federated Pruning in Hierarchical Wireless Networkscited by 10
- 2023Distributed Machine Learning for UAV Swarms: Computing, Sensing, and Semanticscited by 5
- 2024Joint Model Pruning and Resource Allocation for Wireless Time-triggered Federated Learningcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.