MCPST: A Multiphase Consensus and Spatio–Temporal Learning for Few-Shot Traffic Forecasting via Physical Dynamics
IEEE Internet of Things Journal · 2026-08 · 13 (16) · 36234-36254
DOI: 10.1109/jiot.2026.3700641 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, 2026-08. Verfasst von Abdul Joseph Fofanah und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Griffith University.
Abstract (Originalsprache)
Accurate traffic flow prediction remains a fundamental challenge in intelligent transportation systems, particularly in cross-domain, data-scarce scenarios where limited historical data hinders model training and generalization. The complex spatio–temporal dependencies and nonlinear dynamics of urban mobility networks further complicate few-shot learning across different cities. This article proposes MCPST, a novel multiphase consensus spatio–temporal framework for few-shot traffic forecasting that reconceptualises traffic prediction as a multiphase consensus learning problem. Our framework introduces three core innovations: 1) a multiphase engine that models traffic dynamics through diffusion, synchronization, and spectral embeddings for comprehensive dynamics; 2) characterization, an adaptive consensus mechanism that dynamically fuses phase-specific predictions while enforcing consistency; and 3) a structured meta-learning strategy for rapid adaptation to new cities with minimal data. We establish extensive theoretical guarantees, including representation theorems with bounded approximation errors and generalization bounds for few-shot adaptation. Through experiments on four real-world datasets, MCPST achieves competitive performance against 21 state-of-the-art (SOTA) methods in spatio–temporal graph learning, dynamic graph transfer learning, prompt-based spatio–temporal prediction, and cross-domain few-shot settings. Our framework delivers strong average prediction accuracy while requiring up to 90% less training data, and performs on par with the leading baselines in statistically significant comparisons. The implementation code is available at https://github.com/afofanah/MCPST
Förderung
- Griffith University
Zitieren
APA
Fofanah, A. J., Wen, L., & Chen, D. (2026). MCPST: A Multiphase Consensus and Spatio–Temporal Learning for Few-Shot Traffic Forecasting via Physical Dynamics. IEEE Internet of Things Journal, 13(16), 36234-36254. https://doi.org/10.1109/jiot.2026.3700641
Vancouver
Fofanah AJ, Wen L, Chen D. MCPST: A Multiphase Consensus and Spatio–Temporal Learning for Few-Shot Traffic Forecasting via Physical Dynamics. IEEE Internet of Things Journal. 2026;13(16):36234-36254. doi:10.1109/jiot.2026.3700641
BibTeX
@article{Fofanah2026,
author = {Fofanah, Abdul Joseph and Wen, Lian and Chen, David},
title = {MCPST: A Multiphase Consensus and Spatio–Temporal Learning for Few-Shot Traffic Forecasting via Physical Dynamics},
journal = {IEEE Internet of Things Journal},
year = {2026},
volume = {13},
number = {16},
pages = {36234--36254},
doi = {10.1109/jiot.2026.3700641}
}
EUVIMED