{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T06:36:43Z","timestamp":1772087803862,"version":"3.50.1"},"reference-count":57,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JSAN"],"abstract":"<jats:p>Systemic risk propagation in modern financial markets is characterized by non-linear contagion and rapid topological evolution, rendering traditional static monitoring methods ineffective. Existing Graph Neural Networks (GNNs) often struggle to capture \u201cstructural breaks\u201d during crises due to their reliance on static adjacency assumptions and isotropic aggregation. To address these challenges, this study proposes the Temporal Attentive Graph Networks (TAGN), a dynamic framework designed for extreme volatility prediction and financial surveillance. TAGN constructs an incremental multi-scale graph by fusing high-frequency trading data, supply chain linkages, and institutional co-holdings to model heterogeneous risk transmission channels. Technically, it employs a deeply coupled GAT-GRU architecture, where the Graph Attention Network (GAT) dynamically assigns weights to contagion sources, and the Gated Recurrent Unit (GRU) memorizes the trajectory of structural evolution. Extensive experiments on the S&amp;P 500 dataset (2018\u20132024) demonstrate that TAGN significantly outperforms state-of-the-art baselines, including WinGNN and PatchTST, achieving an AUC of 0.890 and a Precision at 50 of 61.5%. Notably, a risk early-warning index derived from TAGN exhibits a 1\u20132 week lead time over the VIX index during major market stress events, such as the Silicon Valley Bank collapse. This research facilitates a paradigm shift from historical statistical estimation to dynamic network-aware sensing, offering interpretable tools for RegTech applications.<\/jats:p>","DOI":"10.3390\/jsan15010023","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:11:28Z","timestamp":1771240288000},"page":"23","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Temporal Attentive Graph Networks for Financial Surveillance: An Incremental Multi-Scale Framework"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3798-4815","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Chengdu Technological University, Chengdu 611730, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7645-9887","authenticated-orcid":false,"given":"Yimin","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chengdu Technological University, Chengdu 611730, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7354-8742","authenticated-orcid":false,"given":"Hang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chengdu Technological University, Chengdu 611730, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8847-482X","authenticated-orcid":false,"given":"Bo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chengdu Technological University, Chengdu 611730, China"}]},{"given":"Xianju","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Chengdu Technological University, Chengdu 611730, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9800-6472","authenticated-orcid":false,"given":"Xiang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510275, China"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3115","DOI":"10.1257\/aer.104.10.3115","article-title":"Financial networks and contagion","volume":"104","author":"Elliott","year":"2014","journal-title":"Am. Econ. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/0304-4076(86)90063-1","article-title":"Generalized autoregressive conditional heteroskedasticity","volume":"31","author":"Bollerslev","year":"1986","journal-title":"J. Econom."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"21435","DOI":"10.1007\/s00521-025-11468-z","article-title":"A GARCH-temporal fusion transformer model for the volatility prediction of exchange traded funds","volume":"37","author":"Petrosino","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Cong, F., Zhang, D., Gong, W., Lin, Q., Feng, W., Dong, Y., and Tang, J. (2023). WinGNN: Dynamic Graph Neural Networks with Random Gradient Aggregation Window. Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD \u201923), Long Beach, CA, USA, 6\u201310 August 2023, Association for Computing Machinery.","DOI":"10.1145\/3580305.3599551"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/TIFS.2025.3607231","article-title":"Multi-Temporal Partitioned Graph Attention Networks for Financial Fraud Detection","volume":"20","author":"Guang","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Nguyen, N.H., Nguyen, T.T., and Ngo, Q.T. (2025). DASF-Net: A Multimodal Framework for Stock Price Forecasting with Diffusion-Based Graph Learning and Optimized Sentiment Fusion. J. Risk Financ. Manag., 18.","DOI":"10.3390\/jrfm18080417"},{"key":"ref_7","unstructured":"Ning, K., Pan, Z., Liu, Y., Jiang, Y., Zhang, J.Y., Rasul, K., Schneider, A., Ma, L., Nevmyvaka, Y., and Song, D. (December, January 30). TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), San Diego, CA, USA."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/s100510050929","article-title":"Hierarchical structure in financial markets","volume":"11","author":"Mantegna","year":"1999","journal-title":"Eur. Phys. J. B-Condens. Matter Complex Syst."},{"key":"ref_9","first-page":"1245","article-title":"FinGAT: Financial Graph Attention Networks for Recommending Top-K Profitable Stocks","volume":"37","author":"Hsu","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_10","first-page":"11820","article-title":"DGA-GNN: Dynamic Grouping Aggregation GNN for Fraud Detection","volume":"38","author":"Duan","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mehrabian, A., Hoseinzade, E., Mazloum, M., and Chen, X. (2025, January 6\u201311). Mamba Meets Financial Markets: A Graph-Mamba Approach for Stock Price Prediction. Proceedings of the ICASSP 2025\u20142025 IEEE International Conference on Acoustics, Speech and Signal Processing, Hyderabad, India.","DOI":"10.1109\/ICASSP49660.2025.10888749"},{"key":"ref_12","unstructured":"Lin, S., Lin, W., Wu, W., Zhao, F., Mo, R., and Zhang, H. (2024, January 7\u201311). SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting. Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wei, J., Yang, S., and Cui, Z. (2025). Integrated GARCH-GRU in Financial Volatility Forecasting. arXiv.","DOI":"10.2139\/ssrn.5215228"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Romero Martinez, M., Carmona Ibanez, P., and Martinez Vargas, J. (2025). Predicting Business Failure with the XGBoost Algorithm: The Role of Environmental Risk. Sustainability, 17.","DOI":"10.3390\/su17114948"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1016\/j.ejor.2009.03.036","article-title":"Support vector machines for default prediction of SMEs based on technology credit","volume":"201","author":"Kim","year":"2010","journal-title":"Eur. J. Oper. Res."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Silva, E., Castilho, D., Pereira, A., and Brandao, H. (2014). A neural network based approach to support the Market Making strategies in High-Frequency Trading. Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN), Beijing, China, 6\u201311 July 2014, IEEE.","DOI":"10.1109\/IJCNN.2014.6889835"},{"key":"ref_17","first-page":"8901","article-title":"MDGNN: Multi-relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction","volume":"38","author":"Qian","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, X., Wang, J., Lan, Y., Jiang, C., and Yuan, X. (2023). MD-GCN: A multi-scale temporal dual graph convolution network for traffic flow prediction. Sensors, 23.","DOI":"10.3390\/s23020841"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zong, X., Chen, Z., Yu, F., and Wei, S. (2024). Local-global spatial-temporal graph convolutional network for traffic flow forecasting. Electronics, 13.","DOI":"10.3390\/electronics13030636"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, C.Y., and Huang, J.J. (2023). Temporal-guided knowledge graph-enhanced graph convolutional network for personalized movie recommendation systems. Future Internet, 15.","DOI":"10.3390\/fi15100323"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ge, Y., Wang, J., Zhang, B., Peng, F., Ma, J., Yang, C., Zhao, Y., and Liu, M. (2024). Spatial-temporal-correlation-constrained dynamic graph convolutional network for traffic flow forecasting. Mathematics, 12.","DOI":"10.3390\/math12193159"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Tanvir, R., Islam, M., Sobhan, M., Luo, D., and Mondal, A. (2024). MOGAT: A multi-omics integration framework using graph attention networks for cancer subtype prediction. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms25052788"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2024.3471571","article-title":"Uncertainty-aware Disentangled Dynamic Graph Attention Network for Out-of-Distribution Generalization","volume":"47","author":"Wang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Xu, F., Wang, N., Wu, H., Wen, X., Zhao, X., and Wan, H. (2024, January 20\u201327). Revisiting Graph-based Fraud Detection in Sight of Heterophily and Spectrum. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i8.28773"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zheng, L., Lu, C., Yuan, J., and Zhu, D. (2024). ChatGPT informed graph neural network for stock movement prediction. arXiv.","DOI":"10.2139\/ssrn.4464002"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_27","unstructured":"Ai, G., Qiao, H., Yan, H., and Pang, G. (2025, January 2\u20137). Semi-supervised Graph Anomaly Detection via Robust Homophily Learning. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), San Diego, CA, USA."},{"key":"ref_28","first-page":"2145","article-title":"Edge-centric temporal GNNs for scalable fraud detection","volume":"36","author":"Lin","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1109\/TKDE.2025.3530467","article-title":"Mitigating the Tail Effect in Fraud Detection by Community Enhanced Multi-Relation Graph Neural Networks","volume":"37","author":"Han","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_30","unstructured":"Choi, J., Kim, H., and Whang, J.J. (March, January 25). Unveiling the Threat of Fraud Gangs to Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA."},{"key":"ref_31","first-page":"107385","article-title":"Forecasting carbon price: A novel multi-factor spatial-temporal GNN framework integrating Graph WaveNet and self-attention mechanism","volume":"131","author":"Xu","year":"2024","journal-title":"Energy Econ."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Xiang, S., Cheng, D., Shang, C., Zhang, Y., and Liang, Y. (2023). Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction. arXiv.","DOI":"10.1145\/3511808.3557089"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tang, Y., and Cai, Z. (2025). iTransformer-FFC: A Frequency-Aware Transformer Framework for Multi-Scale Time Series Forecasting. Electronics, 14.","DOI":"10.3390\/electronics14122378"},{"key":"ref_34","first-page":"11230","article-title":"MASTER: Market-Guided Stock Transformer for Stock Price Forecasting","volume":"38","author":"Li","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_35","unstructured":"Nie, Y., Nguyen, N., Sinthong, P., and Kalagnanam, J. (2023, January 1\u20135). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. Proceedings of the International Conference on Learning Representations (ICLR), Kigali, Rwanda."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Seo, Y., Defferrard, M., Vandergheynst, P., and Bresson, X. (2018). Structured sequence modeling with graph convolutional recurrent networks. Proceedings of the International Conference on Neural Information Processing (ICONIP), Siem Reap, Cambodia, 13\u201316 December 2018, Springer.","DOI":"10.1007\/978-3-030-04167-0_33"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"102660","DOI":"10.1016\/j.irfa.2023.102708","article-title":"Forecasting stock volatility with economic policy uncertainty: A smooth transition GARCH-MIDAS model","volume":"88","author":"Li","year":"2023","journal-title":"Int. Rev. Financ. Anal."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"987","DOI":"10.2307\/1912773","article-title":"Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation","volume":"50","author":"Engle","year":"1982","journal-title":"Econometrica"},{"key":"ref_39","first-page":"106921","article-title":"Network topology analysis of the US banking sector during the Silicon Valley Bank crisis","volume":"155","author":"Silva","year":"2023","journal-title":"J. Bank. Financ."},{"key":"ref_40","first-page":"272","article-title":"A two-factor model for the VIX index","volume":"46","author":"Fernandes","year":"2014","journal-title":"J. Bank. Financ."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.1093\/qje\/qjw018","article-title":"Input specificity and the propagation of idiosyncratic shocks in production networks","volume":"131","author":"Barrot","year":"2016","journal-title":"Q. J. Econ."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1099","DOI":"10.1111\/jofi.12149","article-title":"Connected stocks","volume":"69","author":"Anton","year":"2014","journal-title":"J. Financ."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/S0304-405X(01)00055-1","article-title":"The distribution of realized stock return volatility","volume":"61","author":"Andersen","year":"2001","journal-title":"J. Financ. Econ."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.jfineco.2011.12.010","article-title":"Econometric measures of connectedness and systemic risk in the finance and insurance sectors","volume":"104","author":"Billio","year":"2012","journal-title":"J. Financ. Econ."},{"key":"ref_45","unstructured":"Molnar, C. (2022). Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, Independently Published. Available online: https:\/\/christophm.github.io\/interpretable-ml-book\/."},{"key":"ref_46","unstructured":"Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (May, January 30). Graph attention networks. Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada."},{"key":"ref_47","first-page":"1","article-title":"Representation learning for dynamic graphs: A survey","volume":"21","author":"Kazemi","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: A review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Yang, J., Tang, D., Song, X., Wang, L., Yin, Q., Chen, R., Yu, W., and Zhou, J. (2022). GNNLab: A Factored System for Sample-based GNN Training over GPUs. Proceedings of the 17th European Conference on Computer Systems (EuroSys \u201922), Rennes, France, 5\u20138 April 2022, Association for Computing Machinery.","DOI":"10.1145\/3492321.3519557"},{"key":"ref_50","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume":"Volume 30","author":"Hamilton","year":"2017","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA, 4\u20139 December 2017"},{"key":"ref_51","unstructured":"SEC (2023). Form 13F: Information Required of Institutional Investment Managers."},{"key":"ref_52","first-page":"100742","article-title":"The information content of 13F filings","volume":"59","year":"2022","journal-title":"J. Financ. Mark."},{"key":"ref_53","unstructured":"Taleb, N. (2007). The Black Swan: The Impact of the Highly Improbable, Random House."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollar, P. (2017). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22\u201329 October 2017, IEEE.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_55","first-page":"1","article-title":"Trustworthy AI: A computational perspective","volume":"14","author":"Liu","year":"2023","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_56","unstructured":"He, Y. (2024, January 7\u201311). Continual learning in graph neural networks for evolving fraud patterns. Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria."},{"key":"ref_57","unstructured":"Wang, S. (2024). Stock Volatility Prediction via Bi-level Graph Attention. arXiv."}],"container-title":["Journal of Sensor and Actuator Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2224-2708\/15\/1\/23\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T05:28:22Z","timestamp":1772083702000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2224-2708\/15\/1\/23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,16]]},"references-count":57,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["jsan15010023"],"URL":"https:\/\/doi.org\/10.3390\/jsan15010023","relation":{},"ISSN":["2224-2708"],"issn-type":[{"value":"2224-2708","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,16]]}}}