{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:23:52Z","timestamp":1761582232754,"version":"3.41.0"},"reference-count":41,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Sciences and Engineering Research Council of Canada (NSERC), Discovery Grants program, the Science and Technology Development Fund, Macau SAR","award":["0045\/2019\/AFJ"],"award-info":[{"award-number":["0045\/2019\/AFJ"]}]},{"DOI":"10.13039\/501100004733","name":"University of Macau","doi-asserted-by":"crossref","award":["MYRG2022-00197-FST"],"award-info":[{"award-number":["MYRG2022-00197-FST"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2023,8,31]]},"abstract":"<jats:p>\n            In this article, we formulate lifelong learning as an online transfer learning procedure over consecutive tasks, where learning a given task depends on the accumulated knowledge. We propose a novel theoretical principled framework, lifelong\n            <jats:italic>online<\/jats:italic>\n            learning, where the learning process for each task is in an incremental manner. Specifically, our framework is composed of two-level predictions: the prediction information that is solely from the current task; and the prediction from the knowledge base by previous tasks. Moreover, this article tackled several fundamental challenges: arbitrary or even non-stationary task generation process, an unknown number of instances in each task, and constructing an efficient accumulated knowledge base. Notably, we provide a provable bound of the proposed algorithm, which offers insights on the how the accumulated knowledge improves the predictions. Finally, empirical evaluations on both synthetic and real datasets validate the effectiveness of the proposed algorithm.\n          <\/jats:p>","DOI":"10.1145\/3563947","type":"journal-article","created":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T13:08:32Z","timestamp":1666012112000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Lifelong Online Learning from Accumulated Knowledge"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6447-6559","authenticated-orcid":false,"given":"Changjian","family":"Shui","sequence":"first","affiliation":[{"name":"Universit\u00e9 Laval, Quebec, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9860-4993","authenticated-orcid":false,"given":"William","family":"Wang","sequence":"additional","affiliation":[{"name":"Western University, London, Ontario, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9452-3221","authenticated-orcid":false,"given":"Ihsen","family":"Hedhli","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Laval, Quebec, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1307-6923","authenticated-orcid":false,"given":"Chi Man","family":"Wong","sequence":"additional","affiliation":[{"name":"University of Macau, Taipa, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9359-0737","authenticated-orcid":false,"given":"Feng","family":"Wan","sequence":"additional","affiliation":[{"name":"University of Macau, Taipa, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7413-4162","authenticated-orcid":false,"given":"Boyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Western University, London, Ontario, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3697-4184","authenticated-orcid":false,"given":"Christian","family":"Gagn\u00e9","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Laval, Quebec, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,24]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Pierre Alquier The Tien Mai and Massimiliano Pontil. 2016. Regret bounds for lifelong learning. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research Vol. 54) . Aarti Singh and Jerry Zhu (Eds.). PMLR 261\u2013269. https:\/\/proceedings.mlr.press\/v54\/alquier17a.html."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/app8112321"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.5555\/1622248.1622254"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.5555\/1137817"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/3086758"},{"key":"e_1_3_2_7_2","unstructured":"Alon Cohen and Shie Mannor. 2017. Online learning with many experts. arXiv preprint arXiv:1702.07870 (2017)."},{"key":"e_1_3_2_8_2","unstructured":"Giulia Denevi Carlo Ciliberto Dimitris Stamos and Massimiliano Pontil. 2018. Incremental learning-to-learn with statistical guarantees. In Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence (UAI\u201918) . Amir Globerson and Ricardo Silva (Eds.). AUAI Press Monterey California 457\u2013466. http:\/\/auai.org\/uai2018\/proceedings\/papers\/181.pdf."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014067"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939835"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3201604"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"key":"e_1_3_2_13_2","first-page":"1096","volume-title":"Proceedings of the Conference on Learning Theory","author":"Hazan Elad","year":"2016","unstructured":"Elad Hazan, Tomer Koren, Roi Livni, and Yishay Mansour. 2016. Online learning with low rank experts. In Proceedings of the Conference on Learning Theory. 1096\u20131114."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2905715"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.04.027"},{"key":"e_1_3_2_16_2","unstructured":"Timothy Hospedales Antreas Antoniou Paul Micaelli and Amos Storkey. 2020. Meta-learning in neural networks: A survey. arXiv:2004.05439. Retrieved from https:\/\/arxiv.org\/abs\/2004.05439."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2435209.2435213"},{"key":"e_1_3_2_18_2","unstructured":"David Lopez-Paz and Marc\u2019Aurelio Ranzato. 2017. Gradient episodic memory for continual learning. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach California USA) (NIPS\u201917) . Curran Associates Inc. Red Hook NY 6470\u20136479."},{"key":"e_1_3_2_19_2","first-page":"343","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Maurer Andreas","year":"2013","unstructured":"Andreas Maurer, Massi Pontil, and Bernardino Romera-Paredes. 2013. Sparse coding for multitask and transfer learning. In Proceedings of the International Conference on Machine Learning. 343\u2013351."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3176834"},{"key":"e_1_3_2_21_2","first-page":"287","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Mitchell Tom M.","year":"1993","unstructured":"Tom M. Mitchell and Sebastian B. Thrun. 1993. Explanation-based neural network learning for robot control. In Proceedings of the Advances in Neural Information Processing Systems. 287\u2013294."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974973.77"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_24_2","first-page":"991","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Pentina Anastasia","year":"2014","unstructured":"Anastasia Pentina and Christoph Lampert. 2014. A PAC-bayesian bound for lifelong learning. In Proceedings of the International Conference on Machine Learning. 991\u2013999."},{"key":"e_1_3_2_25_2","first-page":"1540","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Pentina Anastasia","year":"2015","unstructured":"Anastasia Pentina and Christoph H. Lampert. 2015. Lifelong learning with non-iid tasks. In Proceedings of the Advances in Neural Information Processing Systems. 1540\u20131548."},{"key":"e_1_3_2_26_2","first-page":"3612","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Pentina Anastasia","year":"2016","unstructured":"Anastasia Pentina and Ruth Urner. 2016. Lifelong learning with weighted majority votes. In Proceedings of the Advances in Neural Information Processing Systems. 3612\u20133620."},{"key":"e_1_3_2_27_2","unstructured":"Andrei A. Rusu Neil C. Rabinowitz Guillaume Desjardins Hubert Soyer James Kirkpatrick Koray Kavukcuoglu Razvan Pascanu and Raia Hadsell. 2016. Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v27i1.8684"},{"key":"e_1_3_2_29_2","first-page":"507","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ruvolo Paul","year":"2013","unstructured":"Paul Ruvolo and Eric Eaton. 2013. ELLA: An efficient lifelong learning algorithm. In Proceedings of the International Conference on Machine Learning. 507\u2013515."},{"key":"e_1_3_2_30_2","unstructured":"Avishek Saha Piyush Rai Hal Daum\u00c3c III and Suresh Venkatasubramanian. 2011. Online learning of multiple tasks and their relationships. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research Vol. 15) . Geoffrey Gordon David Dunson and Miroslav Dud\u00edk (Eds.). PMLR Fort Lauderdale FL 643\u2013651. https:\/\/proceedings.mlr.press\/v15\/saha11b.html."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3531"},{"key":"e_1_3_2_33_2","unstructured":"Gan Sun Yang Cong and Xiaowei Xu. 2018. Active lifelong learning with \u201cwatchdog\u201d. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and 30th Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligenc. (AAAI\u201918\/IAAI\u201918\/EAAI\u201918) . AAAI Press New Orleans Louisiana Article 503 8 pages."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_2"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9607"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-017-0466-8"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/2499907.2499909"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2747879"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2538028"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.06.003"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3361559"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563947","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3563947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:15Z","timestamp":1750183695000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563947"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,24]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8,31]]}},"alternative-id":["10.1145\/3563947"],"URL":"https:\/\/doi.org\/10.1145\/3563947","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2023,2,24]]},"assertion":[{"value":"2022-02-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-04","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}