Modeling Spatio-Temporal Mobility Across Data Silos via Personalized Federated Learning
IEEE Transactions on Mobile Computing · 2024-12 · 23 (12) · 15289-15306
DOI: 10.1109/tmc.2024.3453657 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-12. Verfasst von Yudong Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 80 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Stable Support for Youth Team in Basic Research Field, Chinese Academy of Sciences.
Themen: Mobilisation
Abstract (Originalsprache)
Spatio-temporal mobility modeling plays a pivotal role in the advancement of mobile computing. Nowadays, data is frequently held by various distributed silos, which are isolated from each other and confront limitations on data sharing. Given this, there have been some attempts to introduce federated learning into spatio-temporal mobility modeling. Meanwhile, the distributional heterogeneity inherent in the spatio-temporal data also puts forward requirements for model personalization. However, the existing methods tackle personalization in a model-centric manner and fail to explore the data characteristics in various data silos, thus ignoring the fact that the fundamental cause of insufficient personalization in the model is the heterogeneous distribution of data. In this paper, we propose a novel distribution-oriented personalized Federated learning framework for Cross-silo Spatio-Temporal mobility modeling (named FedCroST), that leverages learnable spatio-temporal prompts to implicitly represent the local data distribution patterns of data silos and guide the local models to learn the personalized information. Specifically, we focus on the potential characteristics within temporal distribution and devise a conditional diffusion module to generate temporal prompts that serve as guidance for the evolution of the time series. Simultaneously, we emphasize the structure distribution inherent in node neighborhoods and propose adaptive spatial structure partition to construct the spatial prompts, augmenting the spatial information representation. Furthermore, we introduce a denoising autoencoder to effectively harness the learned multi-view spatio-temporal features and obtain personalized representations adapted to local tasks. Our proposal highlights the significance of latent spatio-temporal data distributions in enabling personalized federated spatio-temporal learning, providing new insights into modeling spatio-temporal mobility in data silo scenarios. Extensive experiments conducted on real-world datasets demonstrate that FedCroST outperforms the advanced baselines by a large margin in diverse cross-silo spatio-temporal mobility modeling tasks.
Förderung
- National Natural Science Foundation of China
- Stable Support for Youth Team in Basic Research Field
- Chinese Academy of Sciences
- Natural Science Foundation of Jiangsu Province
- Academic Leaders Cultivation Program, University of Science and Technology of China
Zitieren
APA
Zhang, Y., Wang, X., Wang, P., Wang, B., Zhou, Z., & Wang, Y. (2024). Modeling Spatio-Temporal Mobility Across Data Silos via Personalized Federated Learning. IEEE Transactions on Mobile Computing, 23(12), 15289-15306. https://doi.org/10.1109/tmc.2024.3453657
Vancouver
Zhang Y, Wang X, Wang P, Wang B, Zhou Z, Wang Y. Modeling Spatio-Temporal Mobility Across Data Silos via Personalized Federated Learning. IEEE Transactions on Mobile Computing. 2024;23(12):15289-15306. doi:10.1109/tmc.2024.3453657
BibTeX
@article{Zhang2024,
author = {Zhang, Yudong and Wang, Xu and Wang, Pengkun and Wang, Binwu and Zhou, Zhengyang and Wang, Yang},
title = {Modeling Spatio-Temporal Mobility Across Data Silos via Personalized Federated Learning},
journal = {IEEE Transactions on Mobile Computing},
year = {2024},
volume = {23},
number = {12},
pages = {15289--15306},
doi = {10.1109/tmc.2024.3453657}
}
EUVIMED