Burst-Sensitive Traffic Forecast via Multi-Property Personalized Fusion in Federated Learning

doi:10.1109/TMC.2025.3538871

	Burst-Sensitive Traffic Forecast via Multi-Property Personalized Fusion in Federated Learning
	Xue, Jingjing 1,2; Sun, Sheng 1; Liu, Min 1,2,3; Wang, Yuwei 1; Meng, Xuying 1; Wang, Jingyuan 4,5; Zhang, JunBo 6; Xu, Ke 7,8
	2025-07-01
发表期刊	IEEE TRANSACTIONS ON MOBILE COMPUTING
ISSN	1536-1233
卷号	24 期号:7 页码:5598-5614
摘要	For distributed network traffic prediction with data localization and privacy protection, Federated Learning (FL) enables collaborative training without raw data exchange across Base Stations (BSs). Nevertheless, traffic across BSs exhibit inherently heterogeneous trend burst and smooth fluctuation properties, but existing FL methods model single-scale series from only one view, which cannot simultaneously capture diverse trend and fluctuation properties, especially distinct burst distributions. In this paper, we propose Personalized Federated Forecasting with Multi-property Self-fusion (P2FMS), which can represent multi-scale traffic properties from different views. With precise multi-property representations, a fusion-level prediction decision is learned for each client in a personalized manner to promptly sense traffic bursts and improve forecasting performance in non-IID settings. Specifically, P2FMS decomposes the traffic series into distinct time scales, based on which, we effectively extract closeness, period, and trend properties from different views. The closeness and period are embedded through global-view representations with spatial correlations, while non-stationary trends are individually fitted from the client-side view. Furthermore, a personalized combiner is designed to accurately quantify the proportion of general fluctuation raws (i.e., closeness and period) and specific trend property in predictions, which enables multi-property self-fusion for each client to accommodate heterogeneous traffic patterns and enhance prediction accuracy. Besides, an alternant training mechanism is introduced to optimize property representation and fusion modules with the convergence guarantee. Extensive experiments on real-world datasets show that P2FMS outperforms status quo methods in both prediction performance and convergence time.
关键词	Predictive models Forecasting Data models Market research Fluctuations Computational modeling Training Telecommunication traffic Adaptation models Mathematical models Network traffic forecast federated learning (FL) heterogeneous data multi-scale representation personalized fusion
DOI	10.1109/TMC.2025.3538871
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2021YFB2900102] ; National Natural Science Foundation of China[62472410] ; National Natural Science Foundation of China[62072436] ; National Natural Science Foundation of China[72222022] ; National Natural Science Foundation of China[72171013] ; National Natural Science Foundation of China[7224210] ; National Science Fund for Distinguished Young Scholars of China[62425201] ; National Natural Science Foundation of China ; National Science Fund for Distinguished Young Scholars of China
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Telecommunications
WOS记录号	WOS:001504135300041
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42340
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Min
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Zhongguancun Lab, Beijing 100190, Peoples R China 4.Beihang Univ, Sch Comp Sci & Engn, Beijing 100191, Peoples R China 5.Beihang Univ, MIIT Key Lab Data Intelligence & Management, Beijing 100191, Peoples R China 6.JD Technol, JD Intelligent Cities Res, JD iCity, Beijing 101111, Peoples R China 7.Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100190, Peoples R China 8.Zhongguancun Lab, Beijing 100081, Peoples R China
推荐引用方式 GB/T 7714	Xue, Jingjing,Sun, Sheng,Liu, Min,et al. Burst-Sensitive Traffic Forecast via Multi-Property Personalized Fusion in Federated Learning[J]. IEEE TRANSACTIONS ON MOBILE COMPUTING,2025,24(7):5598-5614.
APA	Xue, Jingjing.,Sun, Sheng.,Liu, Min.,Wang, Yuwei.,Meng, Xuying.,...&Xu, Ke.(2025).Burst-Sensitive Traffic Forecast via Multi-Property Personalized Fusion in Federated Learning.IEEE TRANSACTIONS ON MOBILE COMPUTING,24(7),5598-5614.
MLA	Xue, Jingjing,et al."Burst-Sensitive Traffic Forecast via Multi-Property Personalized Fusion in Federated Learning".IEEE TRANSACTIONS ON MOBILE COMPUTING 24.7(2025):5598-5614.