{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:08:13Z","timestamp":1781194093793,"version":"3.54.1"},"reference-count":35,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,7,30]],"date-time":"2022-07-30T00:00:00Z","timestamp":1659139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"American University of Beirut\u2019s University Research Board"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2022,12,31]]},"abstract":"<jats:p>One key objective of artificial intelligence involves the continuous adaptation of machine learning models to new tasks. This branch of continual learning is also referred to as lifelong learning (LL), where a major challenge is to minimize catastrophic forgetting, or forgetting previously learned tasks. While previous work on catastrophic forgetting has been focused on vision problems; this work targets time-series data. In addition to choosing an architecture appropriate for time-series sequences, our work addresses limitations in previous work, including the handling of distribution shifts in class labels. We present multi-objective learning with three loss functions to minimize catastrophic forgetting, prediction error, and errors in generalizing across label shifts, simultaneously. We build a multi-task autoencoder network with a hierarchical convolutional recurrent architecture. The proposed method is capable of learning multiple time-series tasks simultaneously. For cases where the model needs to learn multiple new tasks, we propose sequential learning, starting with tasks that have the best individual performances. This solution was evaluated on four benchmark human activity recognition datasets collected from mobile sensing devices. A wide set of baseline comparisons is performed, and an ablation analysis is run to evaluate the impact of the different losses in the proposed multi-objective method. The results demonstrate an up to 4% performance improvement in catastrophic forgetting compared to the use of loss functions in state-of-the-art solutions while demonstrating minimal losses compared to upper bound methods of traditional fine-tuning (FT) and multi-task learning (MTL).<\/jats:p>","DOI":"10.1145\/3502728","type":"journal-article","created":{"date-parts":[[2022,6,17]],"date-time":"2022-06-17T09:00:56Z","timestamp":1655456456000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Multi-objective Learning to Overcome Catastrophic Forgetting in Time-series Applications"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9216-2335","authenticated-orcid":false,"given":"Reem A.","family":"Mahmoud","sequence":"first","affiliation":[{"name":"American University of Beirut, and Hazem Hajj, Intel Corporation, Beirut, Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9954-7924","authenticated-orcid":false,"given":"Hazem","family":"Hajj","sequence":"additional","affiliation":[{"name":"American University of Beirut, and Hazem Hajj, Intel Corporation, Hillsboro, OR"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,30]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_1_3_2","unstructured":"Matthias De Lange Rahaf Aljundi Marc Masana Sarah Parisot Xu Jia Ale\u0161 Leonardis Gregory Slabaugh and Tinne Tuytelaars. 2019. A continual learning survey: Defying forgetting in classification tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 7 (2019) 3366\u20133385."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.148"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2011.32"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxt075"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.12.014"},{"key":"e_1_3_1_9_2","volume-title":"Proceedings of the 21st International European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.","author":"Anguita Davide","year":"2013","unstructured":"Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra, and Jorge Luis Reyes-Ortiz. 2013. A public domain dataset for human activity recognition using smartphones. In Proceedings of the 21st International European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8621990"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2538028"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106586"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3369799"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1080\/09540099550039318"},{"key":"e_1_3_1_16_2","first-page":"2672","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the Advances in Neural Information Processing Systems. 2672\u20132680."},{"key":"e_1_3_1_17_2","first-page":"2990","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Shin Hanul","year":"2017","unstructured":"Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. 2017. Continual learning with deep generative replay. In Proceedings of the Advances in Neural Information Processing Systems. 2990\u20132999."},{"key":"e_1_3_1_18_2","first-page":"899","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Xu Ju","year":"2018","unstructured":"Ju Xu and Zhanxing Zhu. 2018. Reinforced continual learning. In Proceedings of the Advances in Neural Information Processing Systems. 899\u2013908."},{"key":"e_1_3_1_19_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."},{"key":"e_1_3_1_20_2","unstructured":"Chrisantha Fernando Dylan Banarse Charles Blundell Yori Zwols David Ha Andrei A. Rusu Alexander Pritzel and Daan Wierstra. 2017. Pathnet: Evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734."},{"key":"e_1_3_1_21_2","unstructured":"Joan Serra Didac Suris Marius Miron and Alexandros Karatzoglou. 2018. Overcoming catastrophic forgetting with hard attention to the task. In International Conference on Machine Learning . PMLR 4548\u20134557."},{"key":"e_1_3_1_22_2","unstructured":"Benedikt Pf\u00fclb and Alexander Gepperth. 2019. A comprehensive application-oriented study of catastrophic forgetting in dnns. arXiv:1905.08101. Retrieved from https:\/\/arxiv.org\/abs\/1905.08101."},{"key":"e_1_3_1_23_2","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume":"70","author":"Zenke Friedemann","year":"2017","unstructured":"Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual learning through synaptic intelligence. Proceedings of Machine Learning Research 70, 3995 (2017), 3987.","journal-title":"Proceedings of Machine Learning Research"},{"key":"e_1_3_1_24_2","unstructured":"Sebastian Farquhar and Yarin Gal. 2018. Towards robust evaluations of continual learning. arXiv:1805.09733. Retrieved from https:\/\/arxiv.org\/abs\/1805.09733."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403234"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2021.03.088"},{"key":"e_1_3_1_27_2","unstructured":"Jianbo Yang Minh Nhut Nguyen Phyo Phyo San Xiaoli Li and Shonali Krishnaswamy. 2015. Deep convolutional neural networks on multichannel time series for human activity recognition. In Proceedings of the 24th International Joint Conference on Artificial Intelligence . 3995\u20134001."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.04.032"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20092498"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052577"},{"key":"e_1_3_1_31_2","unstructured":"Jia Wang Tong Sun Benyuan Liu Yu Cao and Hongwei Zhu. 2021. CLVSA: A convolutional LSTM based variational sequence-to-sequence model with attention for predicting trends of financial markets. arXiv preprint arXiv:2104.04041."},{"key":"e_1_3_1_32_2","unstructured":"G. Hinton O. Vinyals and J. Dean. 2014. Distilling the knowledge in a neural network. NIPS Deep Learning Workshop. arXiv preprint arXiv:1503.02531 2 no. 7."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs11212531"},{"issue":"2011","key":"e_1_3_1_34_2","first-page":"1","article-title":"Sparse autoencoder","volume":"72","author":"Ng Andrew","year":"2011","unstructured":"Andrew Ng. 2011. Sparse autoencoder. CS294A Lecture Notes 72, 2011 (2011), 1\u201319.","journal-title":"CS294A Lecture Notes"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.02.010"},{"key":"e_1_3_1_36_2","first-page":"922","volume-title":"Proceedings of the UAI","author":"Wang Xuezhi","year":"2015","unstructured":"Xuezhi Wang and Jeff G. Schneider. 2015. Generalization bounds for transfer learning under model shift. In Proceedings of the UAI. 922\u2013931."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3502728","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3502728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:47Z","timestamp":1750183787000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3502728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,30]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12,31]]}},"alternative-id":["10.1145\/3502728"],"URL":"https:\/\/doi.org\/10.1145\/3502728","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,30]]},"assertion":[{"value":"2020-11-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}