EUVIMEDEUVIMED entdecken
Crossref

LLM-Augmented Stiefel Graph Neural Networks for Zero-Shot Spatio-Temporal Forecasting

Jiankai Zheng, Liang Xie, Lei Zhu, Guoli Yang

IEEE Transactions on Knowledge and Data Engineering · 2026-07 · 38 (7) · 4477-4490

DOI: 10.1109/tkde.2026.3689935 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-07. Verfasst von Jiankai Zheng und 3 weiteren Autor:innen. Die Arbeit nennt 73 Literaturangaben. Gefördert von: PCL-CMCC Foundation for Science and Innovation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatio-temporal time series (STTS) play a crucial role in domains such as traffic forecasting, energy scheduling, and financial analysis. However, accurate and efficient prediction remains challenging due to the complex dynamic dependencies across temporal and spatial dimensions. Existing Graph Neural Networks (GNNs) often struggle to balance effectiveness and efficiency when modeling dynamic spatio-temporal relations. Meanwhile, Large Language Models (LLMs) exhibit strong capabilities in modeling long-range dependencies and generalization under few-shot and zero-shot conditions, yet their ability to capture spatio-temporal structures remains limited. To address this, we propose LAD-SGNN, a unified framework that integrates the advantages of graph-based and language-based modeling. Specifically, LAD-SGNN employs Spectral Graph Convolution on the Stiefel manifold (SGSC) together with Linear Dynamic Graph Optimization (LDGOSM) to efficiently extract dynamic spatio-temporal features with nearly linear complexity. Structured prompts and a spatio-temporal alignment mechanism are then designed to fuse the extracted dynamic spectral information with task semantics, which are fed into a lightweight LLM to achieve unified modeling of spatio-temporal structures and semantic reasoning. In this framework, SGSC efficiently represents dynamic spatial dependencies in the spectral domain, while the prompt-based alignment strategy explicitly injects spatio-temporal information into the LLM, thereby enhancing generalization across datasets. Extensive experiments on multiple real-world spatio-temporal datasets demonstrate that LAD-SGNN significantly improves prediction accuracy in both zero-shot and few-shot scenarios.

Förderung

  • PCL-CMCC Foundation for Science and Innovation

Zitieren

APA

Zheng, J., Xie, L., Zhu, L., & Yang, G. (2026). LLM-Augmented Stiefel Graph Neural Networks for Zero-Shot Spatio-Temporal Forecasting. IEEE Transactions on Knowledge and Data Engineering, 38(7), 4477-4490. https://doi.org/10.1109/tkde.2026.3689935

Vancouver

Zheng J, Xie L, Zhu L, Yang G. LLM-Augmented Stiefel Graph Neural Networks for Zero-Shot Spatio-Temporal Forecasting. IEEE Transactions on Knowledge and Data Engineering. 2026;38(7):4477-4490. doi:10.1109/tkde.2026.3689935

BibTeX
@article{Zheng2026,
  author = {Zheng, Jiankai and Xie, Liang and Zhu, Lei and Yang, Guoli},
  title = {LLM-Augmented Stiefel Graph Neural Networks for Zero-Shot Spatio-Temporal Forecasting},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {7},
  pages = {4477--4490},
  doi = {10.1109/tkde.2026.3689935}
}
Kostenlos starten →