Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification

2025-06-08 · Jintao Yan, Tan Chen, Yuxuan Sun, Zhaojun Nan, Sheng Zhou, Zhisheng Niu

Asynchronous Federated Learning (AFL) enables distributed model training across multiple mobile devices, allowing each device to independently update its local model without waiting for others. However, device mobility introduces intermittent connectivity, which necessitates gradient sparsification and leads to model staleness, jointly affecting AFL convergence. This paper develops a theoretical model to characterize the interplay among sparsification, model staleness and mobility-induced contact patterns, and their joint impact on AFL convergence. Based on the analysis, we propose a mobility-aware dynamic sparsification (MADS) algorithm that optimizes the sparsification degree based on contact time and model staleness. Closed-form solutions are derived, showing that under low-speed conditions, MADS increases the sparsification degree to enhance convergence, while under high-speed conditions, it reduces the sparsification degree to guarantee reliable uploads within limited contact time. Experimental results validate the theoretical findings. Compared with the state-of-the-art benchmarks, the MADS algorithm increases the image classification accuracy on the CIFAR-10 dataset by 8.76% and reduces the average displacement error in the Argoverse trajectory prediction dataset by 9.46%.

📄 PDF Abstract BibTeX arXiv:2506.07328

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning image-classification Image Classification Trajectory Prediction

Methods 이 논문이 사용한 방법론

Gradient Sparsification Gradient Sparsification is a technique for distributed training that sparsifies stochastic gradients to reduce the communication cost, with minor increase in the number of…

Gradient Sparification for Asynchronous Distributed Training

2019-10-24 · Zijie Yan

Modern large scale machine learning applications require stochastic optimization algorithms to be implemented on distributed computational architectures. A key bottleneck is the communication overhead for exchanging info…

Federated Learning Stochastic Optimization

Efficient Asynchronous Federated Learning with Sparsification and Quantization

2023-12-23 · Juncheng Jia, Ji Liu, Chendi Zhou, Hao Tian 외

While data is distributed in multiple edge devices, Federated Learning (FL) is attracting more and more attention to collaboratively train a machine learning model without transferring raw data. FL generally exploits a p…

Federated Learning Quantization

Mobility-Aware Cooperative Caching in Vehicular Edge Computing Based on Asynchronous Federated and Deep Reinforcement Learning

2022-08-02 · Qiong Wu, Yu Zhao, Qiang Fan, Pingyi Fan 외

The vehicular edge computing (VEC) can cache contents in different RSUs at the network edge to support the real-time vehicular applications. In VEC, owing to the high-mobility characteristics of vehicles, it is necessary…

Deep Reinforcement Learning Edge-computing Federated Learning reinforcement-learning+1

Wireless-Enabled Asynchronous Federated Fourier Neural Network for Turbulence Prediction in Urban Air Mobility (UAM)

2021-12-26 · Tengchan Zeng, Omid Semiari, Walid Saad, Mehdi Bennis

To meet the growing mobility needs in intra-city transportation, the concept of urban air mobility (UAM) has been proposed in which vertical takeoff and landing (VTOL) aircraft are used to provide a ride-hailing service.…

Federated Learning

Accelerating Asynchronous Federated Learning Convergence via Opportunistic Mobile Relaying

2022-06-09 · Jieming Bian, Jie Xu

This paper presents a study on asynchronous Federated Learning (FL) in a mobile network setting. The majority of FL algorithms assume that communication between clients and the server is always available, however, this i…

Attribute Federated Learning