Graph Neural Networks for Systemic Risk Propagation Modeling in Multi-Layer Financial Markets
Keywords:
Graph Neural Networks, systemic risk, financial contagion, multi-layer networks, machine learning in finance, financial infrastructure, risk governanceAbstract
The increasing inter connectivity of modern financial markets has amplified the potential for systemic risk, where distress in one institution or market layer can cascade into widespread instability. Traditional models of financial contagion often rely on single-layer network abstractions or linearized propagation assumptions that fail to capture the complex, non-linear dependencies that characterize today's multi-asset, multi-jurisdictional financial architecture. This paper proposes and analyzes a framework based on Graph Neural Networks (GNNs) designed to model systemic risk propagation across multi-layer financial markets. We examine the structural trade-offs involved in constructing such models, including the representation of heterogeneous node and edge types, the aggregation of information across layers, and the integration of temporal dynamics. From a systems perspective, we discuss the data infrastructure required to support real-time risk monitoring, the computational sustainability of large-scale GNN deployments, and the governance challenges associated with model transparency, fairness, and regulatory oversight. The paper further explores how GNN-based risk models can enhance stress testing, early-warning systems, and macro-prudential policy design. By situating GNNs within the broader socio-technical context of financial regulation and infrastructure, we highlight open problems in robustness, interpretability, and cross-institutional coordination. Our analysis suggests that while GNNs offer significant advantages over classical network models, their deployment in high-stakes financial environments demands careful attention to data leakage, model calibration, and systemic fairness. We conclude by outlining a research agenda that bridges graph representation learning, financial network theory, and responsible AI governance.
References
1. Allen, F., & Gale, D. (2000). Financial contagion. Journal of Political Economy, 108(1), 1–33.
2. Gai, P., & Kapadia, S. (2010). Contagion in financial networks. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 466(2120), 2401–2423.
3. Battaglia, P. W., Hamrick, J. B., Bapst, V., Sanchez-Gonzalez, A., Zambaldi, V., Malinowski, M., ... & Pascanu, R. (2018). Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261.
4. Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (ICLR).
5. Liu, T. (2026). PCA-APT Stress Index for Market Drawdowns.
6. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (NeurIPS), 30.
7. Xue, P., & Ye, Y. (2026). Attention-enhanced reinforcement learning for dynamic portfolio optimization. Intelligent Systems with Applications, 200622.
8. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2018). Graph attention networks. In International Conference on Learning Representations (ICLR).
9. Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems (NeurIPS), 30.
10. Liu, T. (2022, December). Financial Constraint’Impact on Firms’ ESG Rating Based on Chinese Stock Market. In 2022 4th International Conference on Economic Management and Cultural Industry (ICEMCI 2022) (pp. 1085-1095). Atlantis Press.
11. Hu, L., & Shen, Y. (2026). A predictive analytics approach for forecasting global stock index returns using deep learning techniques. Decision Analytics Journal, 100685.
12. Liu, T. (2026). A Comparative Study of Transformer-Based and Classical Models for Financial Time-Series Forecasting. Journal of Risk and Financial Management, 19(3), 203.
13. Liu, T. (2026). Interpretable Machine Learning for Volatility Forecasting Under Realistic Walk-Forward Constraints.
14. Liu, T. (2026). Volatility Forecasting and Early-Warning Market Stress Detection: A Leakage-Safe Evaluation with Tree Ensembles and Transformers.
15. Eisenberg, L., & Noe, T. H. (2001). Systemic risk in financial systems. Management Science, 47(2), 236–249.
16. Brin, S., & Page, L. (1998). The anatomy of a large-scale hypertextual Web search engine. Computer Networks and ISDN Systems, 30(1–7), 107–117.
17. Caccioli, F., Shrestha, M., Moore, C., & Farmer, J. D. (2014). Stability analysis of financial contagion due to overlapping portfolios. Journal of Banking & Finance, 46, 233–245.
18. Poledna, S., Molina-Borboa, J. L., Martínez-Jaramillo, S., van der Leij, M., & Thurner, S. (2015). The multi-layer network nature of systemic risk and its implications for the costs of financial crises. Journal of Financial Stability, 20, 70–81.
19. Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2020). A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 4–24.
20. Xu, K., Hu, W., Leskovec, J., & Jegelka, S. (2019). How powerful are graph neural networks? In International Conference on Learning Representations (ICLR).
21. Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016). Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (pp. 308–318).
22. Chouldechova, A., & Roth, A. (2020). The frontiers of fairness in machine learning. In Machine Learning for Social and Behavioral Change (pp. 1–24). Cambridge University Press.
23. Ying, R., Bourgeois, D., You, J., Zitnik, M., & Leskovec, J. (2019). GNNExplainer: Generating explanations for graph neural networks. In Advances in Neural Information Processing Systems (NeurIPS), 32.
24. Gulrajani, I., & Lopez-Paz, D. (2020). In search of lost domain generalization. In International Conference on Learning Representations (ICLR).
25. Chen, J., Zhu, J., & Song, L. (2018). Stochastic training of graph convolutional networks with variance reduction. In International Conference on Machine Learning (ICML), 80, 941–949.
26. Zügner, D., Akbarnejad, A., & Günnemann, S. (2018). Adversarial attacks on neural networks for graph data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 2847–2856).
27. Bollerslev, T., & Zhou, H. (2006). Volatility puzzles: A simple framework for gauging return-volatility regression. Journal of Econometrics, 131(1–2), 123–150.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Global Financial Analytics Research Review
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
