{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T04:48:07Z","timestamp":1776746887379,"version":"3.51.2"},"reference-count":83,"publisher":"World Scientific Pub Co Pte Ltd","issue":"01","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Semantic Computing"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:p>Dynamic data patterns and adversarial environments present significant challenges for machine learning models in financial service applications, such as fraud detection and financial crime prevention. These systems must continuously adapt to evolving behaviors, requiring frequent model retraining with up-to-date data. However, this introduces a trade-off between incorporating recent trends and preserving valuable historical knowledge, all while managing the scalability of training datasets. Moreover, in high-throughput, time-sensitive deployment scenarios, the latency introduced by retraining can critically impair a model\u2019s ability to respond promptly to emerging threats. Ensuring model agility under strict latency and governance constraints thus becomes a key challenge.<\/jats:p>\n                  <jats:p>In this study, we propose a temporal knowledge distillation (TKD)-based label augmentation framework that leverages insights from prior model generations to accelerate the training of new models. By transferring distilled knowledge from older models to augment the labeling of current training data, our approach significantly reduces retraining time while enhancing model performance. Experimental evaluations demonstrate that the proposed method improves retraining efficiency while consistently enhancing predictive accuracy, training time, model agility and robustness under dynamic, real-world financial conditions.<\/jats:p>","DOI":"10.1142\/s1793351x26500017","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:55:41Z","timestamp":1770976541000},"page":"157-178","source":"Crossref","is-referenced-by-count":0,"title":["Generational Learning for Robust, Agile and Compliant Models in Dynamic Environments Through Temporal Knowledge Distillation"],"prefix":"10.1142","volume":"20","author":[{"given":"Hongda","family":"Shen","sequence":"first","affiliation":[{"name":"University of Alabama in Huntsville, Huntsville, Alabama, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8016-5563","authenticated-orcid":false,"given":"Eren","family":"Kurshan","sequence":"additional","affiliation":[{"name":"Princeton University, Princeton, New Jersey, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"S1793351X26500017BIB001","first-page":"1","volume":"71","author":"Anandakrishnan A.","year":"2017","journal-title":"Proc. Machine Learning Research"},{"key":"S1793351X26500017BIB002","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747908"},{"key":"S1793351X26500017BIB003","author":"Shah A.","year":"2020","journal-title":"Towards DataScience"},{"key":"S1793351X26500017BIB004","first-page":"2654","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Ba J.","year":"2014"},{"key":"S1793351X26500017BIB005","unstructured":"H. Bagherinezhad, M. Horton, M. Rastegari and A. Farhadi, Label refinery: Improving ImageNet classification through label progression, preprint (2018), arXiv:1805.02641."},{"key":"S1793351X26500017BIB006","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"S1793351X26500017BIB007","author":"Buehler K.","year":"2019","journal-title":"McKinsey"},{"key":"S1793351X26500017BIB008","author":"Chatain P. L.","year":"2011","journal-title":"World Bank Report"},{"issue":"1","key":"S1793351X26500017BIB009","volume":"32","author":"Chen C.-Y.","year":"2018","journal-title":"Proc. AAAI Conf. Artif. Int."},{"key":"S1793351X26500017BIB010","unstructured":"D. Chen, J.P. Mei, Y. Zhang, C. Wang, Z. Wang, Y. Feng and C. Chen, Cross-layer distillation with semantic calibration, preprint, arXiv:2012.03236 (2020)."},{"key":"S1793351X26500017BIB011","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Chen G.","year":"2017"},{"key":"S1793351X26500017BIB012","doi-asserted-by":"crossref","unstructured":"T. Chen and C. Guestrin, XGBoost: A scalable tree boosting system, preprint (2016), arXiv:1603.02754.","DOI":"10.1145\/2939672.2939785"},{"key":"S1793351X26500017BIB013","author":"Federal Trade Commission","year":"2024","journal-title":"FTC Portal"},{"key":"S1793351X26500017BIB014","unstructured":"European Payments Council, Payment methods report 2019: Innovations in the way we pay,\n                      E.U. Payments Council Report\n                      (2019)."},{"key":"S1793351X26500017BIB015","first-page":"156","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Daghaghi S.","year":"2021"},{"key":"S1793351X26500017BIB016","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"S1793351X26500017BIB017","unstructured":"T. Devries and G. W. Taylor, Improved regularization of convolutional neural networks with cutout, preprint, arXiv:1708.04552 (2017)."},{"key":"S1793351X26500017BIB018","doi-asserted-by":"publisher","DOI":"10.1142\/S1793351X20300022"},{"key":"S1793351X26500017BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/TransAI49837.2020.00029"},{"key":"S1793351X26500017BIB020","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947008"},{"key":"S1793351X26500017BIB021","doi-asserted-by":"crossref","unstructured":"M. Farhadi and Y. Yang, TKD: Temporal knowledge distillation for active perception, preprint, arXiv:1903.01522 (2019).","DOI":"10.1109\/WACV45572.2020.9093437"},{"key":"S1793351X26500017BIB022","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106883"},{"key":"S1793351X26500017BIB023","unstructured":"World Economic Forum, Transforming paradigms: A global AI in financial services survey (2020)."},{"key":"S1793351X26500017BIB024","unstructured":"T. Furlanello, Z. C. Lipton, M. Tschannen, L. Itti and A. Anandkumar, Born again neural networks, preprint, arXiv:1805.04770 (2018)."},{"key":"S1793351X26500017BIB025","unstructured":"J. Gou, B. Yu, S. J. Maybank and D. Tao, Knowledge distillation: A survey, preprint, arXiv:2006.05525 (2020)."},{"key":"S1793351X26500017BIB026","unstructured":"Y. Gu, L. Dong, F. Wei and M. Huang, MiniLLM: Knowledge distillation of large language models, preprint, arXiv:2306.08543 (2024)."},{"key":"S1793351X26500017BIB027","unstructured":"G. Habib, T. J. Saleem, S. M. Kaleem, T. Rouf and B. Lall, A comprehensive review of knowledge distillation in computer vision, preprint, arXiv:2306.08543 (2024)."},{"key":"S1793351X26500017BIB028","author":"Harrison P.","year":"2020","journal-title":"The Fintech Times"},{"key":"S1793351X26500017BIB029","author":"Hasham S.","year":"2019","journal-title":"McKinsey and Company Report"},{"key":"S1793351X26500017BIB030","unstructured":"J. B. Heaton, N. G. Polson and J. H. Witte, Deep learning in finance, preprint, arXiv:1602.06561 (2016)."},{"key":"S1793351X26500017BIB031","author":"Heun D.","year":"2021","journal-title":"American Banker"},{"key":"S1793351X26500017BIB032","unstructured":"G. Hinton, O. Vinyals and J. Dean, Distilling the knowledge in a neural network, preprint, arXiv:1503.02531 (2015)."},{"key":"S1793351X26500017BIB033","unstructured":"H. Shen and E. Kurshan, Label augmentation via time-based knowledge distillation for financial anomaly detection, preprint, arXiv:2101.01689 (2021)."},{"key":"S1793351X26500017BIB034","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00111"},{"key":"S1793351X26500017BIB035","unstructured":"C. Marfaing and A. Garcia, Computer-assisted fraud detection, from active learning to reward maximization, preprint, arXiv:1811.08212 (2018)."},{"key":"S1793351X26500017BIB036","unstructured":"Mastercard, E-commerce fraud trends and statistics merchants need to know in 2024,\n                      Mastercard News and Insights\n                      (2024)."},{"key":"S1793351X26500017BIB037","unstructured":"A. Matsuo, Regulatory alert: Fraud, identity theft and other scams,\n                      KPMG Regulatory Insights Report\n                      (2024)."},{"key":"S1793351X26500017BIB038","unstructured":"McKinsey and Company, On the cusp of the next payments era: Future opportunities for banks,\n                      McKinsey Report\n                      (2023)."},{"key":"S1793351X26500017BIB039","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.284"},{"key":"S1793351X26500017BIB040","unstructured":"NASDAQ and Verafin, NASDAQ 2024: Global financial crime report, insights at the intersection of financial crime data & real survivor stories, NASDAQ (2024)."},{"key":"S1793351X26500017BIB041","unstructured":"A. Oprea, A. Gal, I. Moulinier, J. Chen, M. Veloso, E. Kurshan, S. Kumar and T. Faruquie, NeurIPS 2019 Workshop on Robust AI in Financial Services: Data, fairness, explainability, trustworthiness, and privacy (2019)."},{"key":"S1793351X26500017BIB042","unstructured":"PRNews, Zelle soars with $806 billion transaction volume, up 28% from prior year (2024)."},{"key":"S1793351X26500017BIB043","unstructured":"Forbes Business Reports, Fraud trends and tectonics, Forbes (2020)."},{"key":"S1793351X26500017BIB044","unstructured":"A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta and Y. Bengio, FitNets: Hints for thin deep nets, preprint, arXiv:1412.6550 (2014)."},{"key":"S1793351X26500017BIB045","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1545"},{"key":"S1793351X26500017BIB046","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432"},{"key":"S1793351X26500017BIB047","unstructured":"V. Sanh, L. Debut, J. Chaumond and T. Wolf, DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter, preprint, arXiv:1910.01108 (2019)."},{"key":"S1793351X26500017BIB048","unstructured":"H. Seo, J. Park, S. Oh, M. Bennis and S.L. Kim, Federated knowledge distillation, preprint, arXiv:2011.02367 (2020)."},{"key":"S1793351X26500017BIB049","author":"Shein E.","year":"2021","journal-title":"TechRepublic"},{"key":"S1793351X26500017BIB050","doi-asserted-by":"crossref","unstructured":"H. Shen and E. Kurshan, Deep Q-network-based adaptive alert threshold selection policy for payment fraud systems in retail banking, preprint, arXiv:2010.11062 (2020).","DOI":"10.1145\/3383455.3422563"},{"key":"S1793351X26500017BIB051","unstructured":"M. Shepard, T. Adams, A. Portilla, M. Ekberg, R. Wainwright, K. Jackson, T. Baumann, C. Bostock, A. Saleh and P. S. Lagoss, The global framework for fighting financial crime: Enhancing effectiveness & improving outcomes,\n                      Deloitte Report\n                      (2019)."},{"key":"S1793351X26500017BIB052","doi-asserted-by":"publisher","DOI":"10.1016\/j.vlsi.2019.09.007"},{"key":"S1793351X26500017BIB053","unstructured":"EWS Early Warning Systems, Zelle digital adoption,\n                      EWS Reports\n                      (2019)."},{"key":"S1793351X26500017BIB054","unstructured":"C. Wang, T. Wang, X. Zhou and H. Chen, A survey of FPGA based deep learning accelerators: Challenges and opportunities, preprint, arXiv:1811.08968 (2018)."},{"key":"S1793351X26500017BIB055","unstructured":"Timeframe Analysis (2019)."},{"key":"S1793351X26500017BIB056","unstructured":"TransUnion, Digital fraud attempts spike 80% globally from pre-pandemic levels,\n                      TransUnion News Report\n                      (2023)."},{"key":"S1793351X26500017BIB057","unstructured":"TransUnion, TransUnion 2024: State of the omnichannel fraud report,\n                      TransUnion\n                      (2024)."},{"key":"S1793351X26500017BIB058","unstructured":"G. Urban, K. Geras, S. E. Kahou, O.\u0308 Aslan, S. Wang, R. Caruana, A. Mohamed, M. Philipose and M. Richardson, Do deep convolutional nets really need to be deep (or even convolutional)? preprint, arXiv:1603.05691 (2016)."},{"key":"S1793351X26500017BIB059","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00367"},{"key":"S1793351X26500017BIB060","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01563"},{"key":"S1793351X26500017BIB061","unstructured":"X. Xu, M. Li, C. Tao, T. Shen, R. Cheng, J. Li, C. Xu, D. Tao and T. Zhou, A survey on knowledge distillation of large language models, preprint, arXiv:2402.13116 (2024)."},{"key":"S1793351X26500017BIB062","author":"Yang Z.","year":"2019","journal-title":"CoRR"},{"key":"S1793351X26500017BIB063","unstructured":"Zelle, Zelle closes 2020 with record $307 billion sent on 1.2 billion transactions,\n                      Zelle Press Releases\n                      (2021)."},{"key":"S1793351X26500017BIB064","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"S1793351X26500017BIB065","unstructured":"H. Zhang, S. Si and C.J. Hsieh, GPU-acceleration for large-scale tree boosting, preprint, arXiv:1706.08359 (2017)."},{"key":"S1793351X26500017BIB066","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00776"},{"key":"S1793351X26500017BIB067","doi-asserted-by":"publisher","DOI":"10.1201\/b12207"},{"key":"S1793351X26500017BIB068","unstructured":"Z. Zhu, J. Hong and J. Zhou, Data-free knowledge distillation for heterogeneous federated learning, preprint, arXiv:2105.10056 (2021)."},{"key":"S1793351X26500017BIB069","first-page":"19","volume":"3","author":"Fern\u00e1ndez A.","year":"2019","journal-title":"Banco de Espana Article"},{"key":"S1793351X26500017BIB070","doi-asserted-by":"publisher","DOI":"10.1108\/IJBM-09-2021-0417"},{"key":"S1793351X26500017BIB071","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75729-8_8"},{"key":"S1793351X26500017BIB072","doi-asserted-by":"publisher","DOI":"10.17148\/IJARCCE.2022.11912"},{"key":"S1793351X26500017BIB073","author":"Calder D.","year":"2023","journal-title":"Ernst and Young Report"},{"key":"S1793351X26500017BIB074","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"S1793351X26500017BIB075","unstructured":"U.S. Federal Trade Commission, New FTC data show a big jump in reported losses to fraud to $12.5 billion in 2024 (March 2025)."},{"key":"S1793351X26500017BIB076","unstructured":"The Clearing House, Real-time payments for all financial institutions (2025)."},{"key":"S1793351X26500017BIB077","unstructured":"ACI Worldwide, Prime time for real-time global payments report (2024)."},{"key":"S1793351X26500017BIB078","unstructured":"Feedzai, More than 50% of fraud driven by AI and hyper-realistic impersonations, but banks also use generative AI to fight back."},{"key":"S1793351X26500017BIB079","unstructured":"Federal Reserve Bank of Kansas City, Card-not-present fraud rates in the United States after the migration to chip cards (2025)."},{"key":"S1793351X26500017BIB080","unstructured":"E. Kursun, System for anomaly detection and remediation based on dynamic directed graph network flow analysis, U.S. Patent 16\/200,065 (2020)."},{"key":"S1793351X26500017BIB081","unstructured":"J. Filliben, E. Kursun, L. C. Edkin, S. A. Sims, C. D. Widmann, M. A. Payne, R. J. Morris and D. M. Pusey-Conlin, Machine learning system to detect, label, and spread heat in a graph structure, U.S. Patent 16\/006,388 (2019)."},{"key":"S1793351X26500017BIB082","unstructured":"R. J. Morris, D. M. Pusey-Conlin, L. C. Edkin, S. A. Sims, J. Filliben, M. A. Payne, C. D. Widmann and E. Kursun, Unsupervised machine learning system to automate functions on a graph structure, U.S. Patent 11,710,033 (2023)."},{"key":"S1793351X26500017BIB083","unstructured":"E. Kursun, Systems and methods for high fidelity multi-modal out-of-band biometric authentication, U.S. Patent 9760785 (2017)."}],"container-title":["International Journal of Semantic Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S1793351X26500017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T04:27:16Z","timestamp":1776745636000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S1793351X26500017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":83,"journal-issue":{"issue":"01","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1142\/S1793351X26500017"],"URL":"https:\/\/doi.org\/10.1142\/s1793351x26500017","relation":{},"ISSN":["1793-351X","1793-7108"],"issn-type":[{"value":"1793-351X","type":"print"},{"value":"1793-7108","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}