Unlocking Dynamic Inter-Client Spatial Dependencies: A Federated Spatio-temporal Graph Learning Method for Traffic Flow Forecasting
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (2) · 1123-1131
DOI: 10.1609/aaai.v40i2.37083 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Feng Wang und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Spatio-temporal graphs are powerful tools for modeling complex dependencies in traffic time series. However, the distributed nature of real-world traffic data across multiple stakeholders poses significant challenges in modeling and reconstructing inter-client spatial dependencies while adhering to data locality constraints. Existing methods primarily address static dependencies, overlooking their dynamic nature and resulting in suboptimal performance. In response, we propose Federated Spatio-Temporal Graph with Dynamic Inter-Client Dependencies (FedSTGD), a framework designed to model and reconstruct dynamic inter-client spatial dependencies in federated learning. FedSTGD incorporates a federated nonlinear computation decomposition module to approximate complex graph operations. This is complemented by a graph node embedding augmentation module, which alleviates performance degradation arising from the decomposition. These modules are coordinated through a client-server collective learning protocol, which decomposes dynamic inter-client spatial dependency learning tasks into lightweight, parallelizable subtasks. Extensive experiments on four real-world datasets demonstrate that FedSTGD achieves superior performance over state-of-the-art baselines in terms of RMSE, MAE, and MAPE, approaching that of centralized baselines. Ablation studies confirm the contribution of each module in addressing dynamic inter-client spatial dependencies, while sensitivity analysis highlights the robustness of FedSTGD to variations in hyperparameters.
Zitieren
APA
Wang, F., Chen, T., Wei, S., Chu, Q., Zhang, Y., Sun, Y., & Zheng, Z. (2026). Unlocking Dynamic Inter-Client Spatial Dependencies: A Federated Spatio-temporal Graph Learning Method for Traffic Flow Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 1123-1131. https://doi.org/10.1609/aaai.v40i2.37083
Vancouver
Wang F, Chen T, Wei S, Chu Q, Zhang Y, Sun Y, et al. Unlocking Dynamic Inter-Client Spatial Dependencies: A Federated Spatio-temporal Graph Learning Method for Traffic Flow Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(2):1123-1131. doi:10.1609/aaai.v40i2.37083
BibTeX
@article{Wang2026,
author = {Wang, Feng and Chen, Tianxiang and Wei, Shuyue and Chu, Qian and Zhang, Yi and Sun, Yifan and Zheng, Zhiming},
title = {Unlocking Dynamic Inter-Client Spatial Dependencies: A Federated Spatio-temporal Graph Learning Method for Traffic Flow Forecasting},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {2},
pages = {1123--1131},
doi = {10.1609/aaai.v40i2.37083}
}
EUVIMED