{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T04:20:17Z","timestamp":1773894017566,"version":"3.50.1"},"reference-count":51,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:00:00Z","timestamp":1772150400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403031"],"award-info":[{"award-number":["62403031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Current artificial intelligence systems have shown excellent performance on the tasks at hand. However, catastrophic forgetting occurs when they learn new tasks. The field of continual learning (CL) investigates the ability to learn a sequence of tasks while being able to deal with earlier tasks well. Typically, current models learn a single latent representation based on the class label for each task in this context. To overcome this, we propose a novel approach, called Online Continual Learning via the Feature Enhancement Network (OCLFEN), which integrates an auto\u2010encoder framework to learn example\u2010level representation features using reconstruction loss from the data itself. This strategy enhances latent discriminative representations. Additionally, we incorporate relationship distillation loss to transfer similarity relationships between current and previous models, further mitigating catastrophic forgetting. Extensive experiments on various benchmarks and under different conditions demonstrate that OCLFEN proposed in this paper outperforms state\u2010of\u2010the\u2010art algorithms, highlighting its effectiveness and robustness in CL scenarios. The project page will be available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/sunlight-622\/OCL_FEN\">https:\/\/github.com\/sunlight\u2010622\/OCL_FEN<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1111\/exsy.70231","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T09:57:15Z","timestamp":1772963835000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Online Continual Learning via the Feature Enhancement Network"],"prefix":"10.1111","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0695-5604","authenticated-orcid":false,"given":"Ya\u2010nan","family":"Han","sequence":"first","affiliation":[{"name":"Tianmushan Laboratory  Hangzhou China"},{"name":"School of Automation Science and Electrical Engineering, Beihang University  Beijing China"}]},{"given":"Zong\u2010xia","family":"Jiao","sequence":"additional","affiliation":[{"name":"Tianmushan Laboratory  Hangzhou China"},{"name":"School of Automation Science and Electrical Engineering, Beihang University  Beijing China"},{"name":"Ningbo Institute of Technology, Beihang University  Ningbo China"}]},{"given":"Xiao\u2010chao","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianmushan Laboratory  Hangzhou China"},{"name":"Ningbo Institute of Technology, Beihang University  Ningbo China"},{"name":"Research Institute for Frontier Science, Beihang University  Beijing China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2042-915X","authenticated-orcid":false,"given":"Peng\u2010yuan","family":"Qi","sequence":"additional","affiliation":[{"name":"Tianmushan Laboratory  Hangzhou China"},{"name":"Ningbo Institute of Technology, Beihang University  Ningbo China"},{"name":"Research Institute for Frontier Science, Beihang University  Beijing China"}]}],"member":"311","published-online":{"date-parts":[[2026,2,27]]},"reference":[{"key":"e_1_2_10_2_1","first-page":"11816","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Aljundi R.","year":"2019"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_2_10_4_1","first-page":"15920","article-title":"Dark Experience for General Continual Learning: A Strong, Simple Baseline","volume":"33","author":"Buzzega P.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"e_1_2_10_6_1","first-page":"9496","volume-title":"Co2L: Contrastive Continual Learning","author":"Cha H.","year":"2021"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"e_1_2_10_8_1","volume-title":"BT\u20147th International Conference on Learning Representations","author":"Chaudhry A.","year":"2019"},{"key":"e_1_2_10_9_1","unstructured":"Chaudhry A. M.Rohrbach M.Elhoseiny et\u00a0al.2019. \u201cOn Tiny Episodic Memories in Continual Learning.\u201d arXiv:1902.10486."},{"issue":"7","key":"e_1_2_10_10_1","first-page":"3366","article-title":"A Continual Learning Survey: Defying Forgetting in Classification Tasks","volume":"44","author":"Delange M.","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_23"},{"key":"e_1_2_10_12_1","first-page":"1920","volume-title":"Online Meta\u2010Learning. BT\u2014Proceedings of the 36th International Conference on Machine Learning","author":"Finn C.","year":"2019"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/0470018860.s00096"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559\u2010016\u20109389\u20105"},{"key":"e_1_2_10_15_1","volume-title":"Deep Learning. In Adaptive Computation and Machine Learning","author":"Goodfellow I. J.","year":"2016"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.03.006"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.09.004"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892898"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104966"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01394"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_10_22_1","unstructured":"Hinton G. E. O.Vinyals andJ.Dean.2015.\u201cDistilling the Knowledge in a Neural Network \u201dpreprint arXiv 1503.02531."},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_41"},{"key":"e_1_2_10_25_1","volume-title":"BT\u20146th International Conference on Learning Representations","author":"Kemker R.","year":"2018"},{"issue":"13","key":"e_1_2_10_26_1","first-page":"3521","article-title":"Overcoming Catastrophic Forgetting in Neural Networks","volume":"1612","author":"Kirkpatrick J.","year":"2016","journal-title":"Communications in Statistics\u2014Simulation and Computation"},{"key":"e_1_2_10_27_1","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky G.","year":"2009"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_37"},{"key":"e_1_2_10_29_1","first-page":"17","volume-title":"CORe50: A New Dataset and Benchmark for Continuous Object Recognition. BT \u2010 1st Annual Conference on Robot Learning","author":"Lomonaco V.","year":"2017"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.03.010"},{"key":"e_1_2_10_31_1","first-page":"33","volume-title":"Memory Replay With Data Compression for Continual Learning","author":"Munkhdalai T.","year":"2022"},{"key":"e_1_2_10_32_1","unstructured":"Nichol A. J.Achiam andJ.Schulman.2018. \u201cOn First\u2010Order Meta\u2010Learning Algorithms.\u201d arXiv preprint arXiv:1803.02999."},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"e_1_2_10_34_1","first-page":"1","volume-title":"DualNet: Continual Learning, Fast and Slow","author":"Pham Q.","year":"2021"},{"key":"e_1_2_10_35_1","first-page":"1","article-title":"Bilevel Continual Learning","volume":"2007","author":"Pham Q.","year":"2020","journal-title":"arXiv Prepr. arXiv2007.15553"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.093"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"e_1_2_10_38_1","volume-title":"BT\u20147th International Conference on Learning Representations","author":"Riemer M.","year":"2019"},{"key":"e_1_2_10_39_1","volume-title":"Continual Learning in Reinforcement Environments","author":"Ring M. B.","year":"1995"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ANNES.1993.323080"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1080\/09540099550039318"},{"key":"e_1_2_10_42_1","unstructured":"Rusu A. A. N. C.Rabinowitz G.Desjardins et\u00a0al.2016.\u201cProgressive Neural Networks.\u201dpreprint arXiv 1606.04671 vol. abs\/1606.0.http:\/\/arxiv.org\/abs\/1606.04671."},{"key":"e_1_2_10_43_1","first-page":"2660","volume-title":"Online Deep Learning: Learning Deep Neural Networks on the Fly. BT \u2010 Proceedings of the Twenty\u2010Seventh International Joint Conference on Artificial Intelligence","author":"Sahoo D.","year":"2018"},{"key":"e_1_2_10_44_1","first-page":"4555","volume-title":"BT\u2014Proceedings of the 35th International Conference on Machine Learning","author":"Serr\u00e0 J.","year":"2018"},{"key":"e_1_2_10_45_1","first-page":"9630","volume-title":"Thirty\u2010Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty\u2010Third Conference on Innovative Applications of Artificial Intelligence","author":"Shim D.","year":"2021"},{"key":"e_1_2_10_46_1","first-page":"2990","volume-title":"BT\u2014Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems","author":"Shin H.","year":"2017"},{"key":"e_1_2_10_47_1","first-page":"201","volume-title":"A Lifelong Learning Perspective for Mobile Robot Control. BT\u2014Intelligent Robots and Systems, Selections of the International Conference on Intelligent Robots and Systems 1994","author":"Thrun S.","year":"1994"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2"},{"key":"e_1_2_10_49_1","unstructured":"van deVen G. M. andA. S.Tolias.2019.\u201cThree Scenarios for Continual Learning.\u201dpreprint arXiv. 1904.07734 1\u201318.http:\/\/arxiv.org\/abs\/1904.07734."},{"key":"e_1_2_10_50_1","volume-title":"The Caltech\u2010Ucsd Birds\u2010200\u20102011 Dataset","author":"Wah C.","year":"2011"},{"key":"e_1_2_10_51_1","volume-title":"BT\u20146th International Conference on Learning Representations","author":"Yoon J.","year":"2018"},{"key":"e_1_2_10_52_1","first-page":"3987","volume-title":"BT\u2014Proceedings of the 34th International Conference on Machine Learning","author":"Zenke F.","year":"2017"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70231","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70231","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T02:01:40Z","timestamp":1773885700000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70231"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,27]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1111\/exsy.70231"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70231","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,27]]},"assertion":[{"value":"2025-04-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70231"}}