Efficient Federated Learning with Timely Update Dissemination
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913932345606144 |
|---|---|
| author | Jia, Juncheng Liu, Ji Huo, Chao Shen, Yihui Zhou, Yang Dai, Huaiyu Dou, Dejing |
| author_facet | Jia, Juncheng Liu, Ji Huo, Chao Shen, Yihui Zhou, Yang Dai, Huaiyu Dou, Dejing |
| contents | Federated Learning (FL) has emerged as a compelling methodology for the management of distributed data, marked by significant advancements in recent years. In this paper, we propose an efficient FL approach that capitalizes on additional downlink bandwidth resources to ensure timely update dissemination. Initially, we implement this strategy within an asynchronous framework, introducing the Asynchronous Staleness-aware Model Update (FedASMU), which integrates both server-side and device-side methodologies. On the server side, we present an asynchronous FL system model that employs a dynamic model aggregation technique, which harmonizes local model updates with the global model to enhance both accuracy and efficiency. Concurrently, on the device side, we propose an adaptive model adjustment mechanism that integrates the latest global model with local models during training to further elevate accuracy. Subsequently, we extend this approach to a synchronous context, referred to as FedSSMU. Theoretical analyses substantiate the convergence of our proposed methodologies. Extensive experiments, encompassing six models and five public datasets, demonstrate that FedASMU and FedSSMU significantly surpass baseline methods in terms of both accuracy (up to 145.87%) and efficiency (up to 97.59%). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06031 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Federated Learning with Timely Update Dissemination Jia, Juncheng Liu, Ji Huo, Chao Shen, Yihui Zhou, Yang Dai, Huaiyu Dou, Dejing Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Federated Learning (FL) has emerged as a compelling methodology for the management of distributed data, marked by significant advancements in recent years. In this paper, we propose an efficient FL approach that capitalizes on additional downlink bandwidth resources to ensure timely update dissemination. Initially, we implement this strategy within an asynchronous framework, introducing the Asynchronous Staleness-aware Model Update (FedASMU), which integrates both server-side and device-side methodologies. On the server side, we present an asynchronous FL system model that employs a dynamic model aggregation technique, which harmonizes local model updates with the global model to enhance both accuracy and efficiency. Concurrently, on the device side, we propose an adaptive model adjustment mechanism that integrates the latest global model with local models during training to further elevate accuracy. Subsequently, we extend this approach to a synchronous context, referred to as FedSSMU. Theoretical analyses substantiate the convergence of our proposed methodologies. Extensive experiments, encompassing six models and five public datasets, demonstrate that FedASMU and FedSSMU significantly surpass baseline methods in terms of both accuracy (up to 145.87%) and efficiency (up to 97.59%). |
| title | Efficient Federated Learning with Timely Update Dissemination |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2507.06031 |