Federated graph learning with spatio-temporal dynamics for cross-border recommendation
- 1School of Computer Science and Engineering, Macau University of Science and Technology
Abstract
Cross-border data sharing is strictly constrained by privacy regulations, which presents a critical challenge for recommendation systems due to the severe shortage of training data. Existing federated graph neural network methods predominantly rely on the federated averaging strategy, which struggles to handle the highly heterogeneous data encountered in scenarios characterized by user isolation and business homogeneity. To address this issue, this paper proposes FedSTAR, a privacy-preserving cross-border recommendation framework that integrates spatio-temporal dynamic modeling with federated graph neural networks. Its core innovations include the design of a dynamic sequential graph structure to capture the evolution of user preferences, the use of a multi-head attention mechanism to filter noisy neighbors in the spatial dimension, and the introduction of a personalized federated aggregation strategy to replace traditional FedAvg, thereby enabling adaptive fusion of heterogeneous multi-source data. Evaluations on three public datasets, Gowalla, Yelp 2018, and Amazon Book, demonstrate that FedSTAR achieves average improvements of 2–5 percentage points in Recall@20 and 1–3 percentage points in NDCG@20, respectively. Under the privacy constraint of exchanging only model updates, FedSTAR delivers both high accuracy and strong robustness, offering a secure and practically viable solution for cross-border recommendation.
Related
- KT-CBHNET: a spatio-temporal deep learning framework for interpretable ECG signal classification for cardiovascular disease prediction
- Advanced optical polarimetric microscopy reveals spatio-temporal dynamics of cervix remodeling during gestation
- Fine-scale spatio-temporal dynamics of kdr mutation V1016G in Aedes albopictus along a transect encompassing the Rome metropolitan area.
- Spatio-temporal dynamics, transmission hotspots, and vaccination gaps driving measles persistence in Nigeria, 2006–2025
- Attention-based Spatio-Temporal Graph Convolutional Networks-enhanced deep reinforcement learning for adaptive traffic signal control in urban traffic networks
BibTeX
@article{tan2026federated,
title = {{Federated graph learning with spatio-temporal dynamics for cross-border recommendation}},
author = {Zhizhong Tan and Yuheng Wang and Jiexin Zheng and Ningning Zhang and Chi Zhang and Wenyong Wang},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-60810-5},
url = {https://doi.org/10.1038/s41598-026-60810-5},
note = {CC BY},
}
RIS
TY - JOUR
TI - Federated graph learning with spatio-temporal dynamics for cross-border recommendation
AU - Zhizhong Tan
AU - Yuheng Wang
AU - Jiexin Zheng
AU - Ningning Zhang
AU - Chi Zhang
AU - Wenyong Wang
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-60810-5
UR - https://doi.org/10.1038/s41598-026-60810-5
AB - Cross-border data sharing is strictly constrained by privacy regulations, which presents a critical challenge for recommendation systems due to the severe shortage of training data. Existing federated graph neural network methods predominantly rely on the federated averaging strategy, which struggles to handle the highly heterogeneous data encountered in scenarios characterized by user isolation and business homogeneity. To address this issue, this paper proposes FedSTAR, a privacy-preserving cross-border recommendation framework that integrates spatio-temporal dynamic modeling with federated graph neural networks. Its core innovations include the design of a dynamic sequential graph structure to capture the evolution of user preferences, the use of a multi-head attention mechanism to filter noisy neighbors in the spatial dimension, and the introduction of a personalized federated aggregation strategy to replace traditional FedAvg, thereby enabling adaptive fusion of heterogeneous multi-source data. Evaluations on three public datasets, Gowalla, Yelp 2018, and Amazon Book, demonstrate that FedSTAR achieves average improvements of 2–5 percentage points in Recall@20 and 1–3 percentage points in NDCG@20, respectively. Under the privacy constraint of exchanging only model updates, FedSTAR delivers both high accuracy and strong robustness, offering a secure and practically viable solution for cross-border recommendation.
SN - 2045-2322
ER -