A Micro-Manifold Identity-Preserving Spatiotemporal Graph Neural Network for Financial Risk Early Warning
Mathematics · 21.04.2026 · 14 (8) · 1388
DOI: 10.3390/math14081388 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 21.04.2026. Verfasst von Jin Kuang und 3 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cultivation of Leading Talents in Planning of Philosophy and Social Sciences in Zhejiang Province, Zhejiang international studies university Institute of Advanced Studies in New International Relations Major project.
Abstract (Originalsprache)
Traditional financial early warning models often rely on the independent and identically distributed (IID) assumption, failing to adequately capture cross-sectional spatial contagion effects and temporal dynamic mutations, and are susceptible to the over-smoothing problem when processing highly imbalanced graph networks. To address these limitations, this study proposes a micro-manifold-based identity-preserving spatiotemporal graph neural network framework (Micro-STAGNN). In the spatial dimension, an identity-preserving graph convolutional operator (IP-GCN) is constructed. By hard-coding a self-preservation coefficient (λ=0.8), it quantifies peer risk spillover while mitigating feature dilution, ensuring the transmission of heterogeneous default signals. In the temporal dimension, Long Short-Term Memory networks are cascaded with a temporal attention mechanism to capture the nonlinear temporal inflection points that trigger financial distress. The empirical study utilizes a sample of China’s A-share market from 2015 to 2025, evaluating the model using an Out-of-Time Validation protocol and Focal Loss. Results indicate that under a highly imbalanced distribution with a positive-to-negative sample ratio of approximately 1:50, Micro-STAGNN achieves an OOT ROC-AUC of 0.9095, a minority class default recall of 89%, and reduces the missed detection rate to 11%, outperforming traditional nonlinear cross-sectional models such as XGBoost. Furthermore, temporal attention weights provide explainable support for the early warning results.
Förderung
- Cultivation of Leading Talents in Planning of Philosophy and Social Sciences in Zhejiang Province
- Zhejiang international studies university Institute of Advanced Studies in New International Relations Major project
Zitieren
APA
Kuang, J., Chen, F., Guo, T., & Chu, C. (2026). A Micro-Manifold Identity-Preserving Spatiotemporal Graph Neural Network for Financial Risk Early Warning. Mathematics, 14(8), 1388. https://doi.org/10.3390/math14081388
Vancouver
Kuang J, Chen F, Guo T, Chu C. A Micro-Manifold Identity-Preserving Spatiotemporal Graph Neural Network for Financial Risk Early Warning. Mathematics. 2026;14(8):1388. doi:10.3390/math14081388
BibTeX
@article{Kuang2026,
author = {Kuang, Jin and Chen, Fusheng and Guo, Te and Chu, Chiawei},
title = {A Micro-Manifold Identity-Preserving Spatiotemporal Graph Neural Network for Financial Risk Early Warning},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {8},
pages = {1388},
doi = {10.3390/math14081388}
}
EUVIMED