Loss-Responsive Dual-Memory Graph Models for Fraud Drift: A Controlled Temporal Stress Test
DOI:
https://doi.org/10.54097/h9r3cp18Keywords:
Financial fraud detection, Concept drift, Graph neural networks, Online adaptation, Synthetic benchmarking, Dual memoryAbstract
Adaptive graph fraud detectors must decide both when to update and how strongly to trust an updated model. This study isolates those decisions through a fully reproducible synthetic temporal-transaction benchmark. Following the ATGNN-SP design, we implement directed two-hop simplified graph propagation, a frozen stable model, an incrementally updated plastic model, a validation-calibrated loss gate, and anchor replay. We extend the fixed stable–plastic mixture with a delayed-label exponential expert-weighting rule. Across five seeds and 15 future snapshots, the adaptive mixture attains average precision 0.4170 and F1 0.4021, versus 0.3469 and 0.3189 for a fixed mixture; however, it updates on all 15 snapshots, compared with 7.8 for the fixed mixture. Plastic-only adaptation is competitive (AP 0.4163; F1 0.3965), showing that retaining a frozen predictor in the final score need not always improve outcomes. All results are computed from a synthetic generator with deliberately changing label and connectivity mechanisms; they should be interpreted as a controlled stress test, not empirical validation on banking or cryptocurrency transactions.
Downloads
References
[1] Weber, M., Domeniconi, G., Chen, J., Weidele, D. K. I., Bellei, C., Robinson, T., & Leiserson, C. E. (2019). Anti-money laundering in Bitcoin: Experimenting with graph convolutional networks for financial forensics. arXiv, arXiv:1908.02591. https://doi.org/10.48550/arXiv.1908.02591
[2] Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR).
[3] Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., & Weinberger, K. Q. (2019). Simplifying graph convolutional networks. In Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97 (pp. 6861-6871). PMLR.
[4] Yue, X., Yang, J., Zhu, R., & Xu, Q. (2026). Adaptive temporal graph neural networks for real-time financial fraud detection under concept drift. Highlights in Business, Economics and Management, 69, 239-250. https://doi.org/10.54097/c8364y03
[5] Hamilton, W. L., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, 30, 1024-1034.
[6] Wang, J., Liu, J., Ge, Y., & Jiang, B. (2023). Risk-aware ensemble learning for credit default prediction under economic uncertainty. World Journal of Economics and Business Research, 1(1), 18-32.
[7] Pareja, A., Domeniconi, G., Chen, J., Ma, T., Suzumura, T., Kanezashi, H., Kaler, T., Schardl, T. B., & Leiserson, C. E. (2020). EvolveGCN: Evolving graph convolutional networks for dynamic graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 34(4), 5363-5370. https://doi.org/10.1609/aaai.v34i04.5984
[8] Xu, D., Ruan, C., Körpeoğlu, E., Kumar, S., & Achan, K. (2020). Inductive representation learning on temporal graphs. In Proceedings of the International Conference on Learning Representations (ICLR).
[9] Kumar, S., Zhang, X., & Leskovec, J. (2019). Predicting dynamic embedding trajectory in temporal interaction networks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (pp. 1269-1278). ACM. https://doi.org/10.1145/3292500.3330895
[10] Sankar, A., Wu, Y., Gou, L., Zhang, W., & Sundaram, H. (2020). DySAT: Deep neural representation learning on dynamic graphs via self-attention networks. In Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM) (pp. 519-527). ACM. https://doi.org/10.1145/3336191.3371845
[11] Rossi, E., Chamberlain, B., Frasca, F., Eynard, D., Monti, D., & Bronstein, M. M. (2020). Temporal graph networks for deep learning on dynamic graphs. arXiv, arXiv:2006.10637. https://doi.org/10.48550/arXiv.2006.10637
[12] Dou, Y., Liu, Z., Sun, L., Deng, Y., Peng, H., & Yu, P. S. (2020). Enhancing graph neural network-based fraud detectors against camouflaged fraudsters. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM) (pp. 315-324). ACM. https://doi.org/10.1145/3340531.3411980
[13] Wang, J., Ge, Y., Liu, J., & Jiang, B. (2024). Early warning of liquidity stress in U.S. banks with seasonally aligned frailty hazards and delayed-feedback conformal alarms. Journal of Trends in Finance and Economics, 1(1), 85-100.
[14] Akoglu, L., Tong, H., & Koutra, D. (2015). Graph based anomaly detection and description: A survey. Data Mining and Knowledge Discovery, 29, 626-688. https://doi.org/10.1007/s10618-014-0365-y
[15] Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), Article 15. https://doi.org/10.1145/1541880.1541882
[16] Elmougy, Y., & Liu, L. (2023). Demystifying fraudulent transactions and illicit nodes in the Bitcoin network for financial forensics. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (pp. 3979-3990). ACM. https://doi.org/10.1145/3580305.3599803
[17] Lorenz, J., Silva, M. I., Aparício, D., Ascensão, J. T., & Bizarro, P. (2020). Machine learning methods to detect money laundering in the Bitcoin blockchain in the presence of label scarcity. In Proceedings of the 1st ACM International Conference on AI in Finance (ICAIF). ACM. https://doi.org/10.1145/3383455.3422549
[18] Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., & Bouchachia, A. (2014). A survey on concept drift adaptation. ACM Computing Surveys, 46(4), Article 44. https://doi.org/10.1145/2523813
[19] Lu, J., Liu, A., Dong, F., Gu, F., Gama, J., & Zhang, G. (2019). Learning under concept drift: A review. IEEE Transactions on Knowledge and Data Engineering, 31(12), 2346-2363. https://doi.org/10.1109/TKDE.2018.2876857
[20] Bifet, A., & Gavaldà, R. (2007). Learning from time-changing data with adaptive windowing. In Proceedings of the SIAM International Conference on Data Mining (SDM) (pp. 443-448). SIAM. https://doi.org/10.1137/1.9781611972771.42
[21] Page, E. S. (1954). Continuous inspection schemes. Biometrika, 41(1-2), 100-115. https://doi.org/10.1093/biomet/41.1-2.100
[22] He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263-1284. https://doi.org/10.1109/TKDE.2008.239
[23] Saito, T., & Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLOS ONE, 10(3), Article e0118432. https://doi.org/10.1371/journal.pone.0118432
[24] Breiman, L. (2001). Random forests. Machine Learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
[25] Teng, D. (2025). RSRBench: Reproducibility and performance benchmarking for regional seismic risk workflows. Academic Journal of Architecture and Civil Engineering, 3(1), 40-52.
[26] Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825-2830.
[27] Cesa-Bianchi, N., & Lugosi, G. (2006). Prediction, learning, and games. Cambridge University Press.
[28] Yue, X., Yang, J., & Liu, W. (2026). FRAUDDEBATE-AGENT: A multi-agent LLM framework with an evidence-based debate mechanism for financial statement fraud detection. Mathematics, 14, Article 2695. https://doi.org/10.3390/math14152695
[29] Fan, H., Jiao, Y., Wang, M., Chen, J., & Yang, S. (2026). Fraud learns too: Continual graph learning under strategic adversarial drift in dynamic networks. Scientific Reports, 16, Article 60997. https://doi.org/10.1038/s41598-026-60997-7
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Computing and Electronic Information Management
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
