{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:38:27Z","timestamp":1770273507935,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of Guangdong Province of China","award":["No. 2019A1515011705"],"award-info":[{"award-number":["No. 2019A1515011705"]}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Program","doi-asserted-by":"publisher","award":["No. KQTD20190929172835662"],"award-info":[{"award-number":["No. KQTD20190929172835662"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Basic Research Foundation","award":["No. JCYJ20200109113441941"],"award-info":[{"award-number":["No. JCYJ20200109113441941"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 61906185, 92046003, 61976204, U1811461"],"award-info":[{"award-number":["No. 61906185, 92046003, 61976204, U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovation Promotion Association of CAS China","award":["No. 2020357"],"award-info":[{"award-number":["No. 2020357"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462902","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T03:08:41Z","timestamp":1626059321000},"page":"1229-1238","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification"],"prefix":"10.1145","author":[{"given":"Binzong","family":"Geng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China & Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fajie","family":"Yuan","sequence":"additional","affiliation":[{"name":"Westlake University & Tencent, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shupeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Ao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruifeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Hongjoon Ahn Sungmin Cha Donggyu Lee and Taesup Moon. 2019. Uncertainty-based continual learning with adaptive regularization. In NeurIPS . 4392--4402."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Rahaf Aljundi Klaas Kelchtermans and Tinne Tuytelaars. 2019. Task-free continual learning. In CVPR. 11254--11263.","DOI":"10.1109\/CVPR.2019.01151"},{"key":"e_1_3_2_2_3_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_2_4_1","unstructured":"John Blitzer Mark Dredze and Fernando Pereira. 2007. Biographies bollywood boom-boxes and blenders: Domain adaptation for sentiment classification. In ACL. 440--447."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"John Blitzer Ryan McDonald and Fernando Pereira. 2006. Domain adaptation with structural correspondence learning. In EMNLP. 120--128.","DOI":"10.3115\/1610075.1610094"},{"key":"e_1_3_2_2_6_1","volume-title":"Weight uncertainty in neural networks. arXiv preprint arXiv:1505.05424","author":"Blundell Charles","year":"2015","unstructured":"Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, and Daan Wierstra. 2015. Weight uncertainty in neural networks. arXiv preprint arXiv:1505.05424 (2015)."},{"key":"e_1_3_2_2_7_1","unstructured":"Zhiyuan Chen Nianzu Ma and Bing Liu. 2015. Lifelong learning for sentiment classification. In ACL. 750--756."},{"key":"e_1_3_2_2_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. NAACL","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. NAACL (2019)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.370"},{"key":"e_1_3_2_2_10_1","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: 1701.08734 [cs.NE]"},{"key":"e_1_3_2_2_11_1","unstructured":"Xavier Glorot Antoine Bordes and Yoshua Bengio. 2011. Domain adaptation for large-scale sentiment classification: A deep learning approach. In ICML. 513--520."},{"key":"e_1_3_2_2_12_1","unstructured":"Alex Graves. 2011. Practical Variational Inference for Neural Networks. In Advances in Neural Information Processing Systems 24. 2348--2356."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Jiang Guo Darsh J Shah and Regina Barzilay. 2018. Multi-source domain adaptation with mixture of experts. In EMNLP. 4694--4703.","DOI":"10.18653\/v1\/D18-1498"},{"key":"e_1_3_2_2_15_1","volume-title":"Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882","author":"Kim Yoon","year":"2014","unstructured":"Yoon Kim. 2014. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_2_18_1","volume-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. arxiv","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. arxiv: 1909.11942 [cs.CL]"},{"key":"e_1_3_2_2_19_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_20_1","unstructured":"David Lopez-Paz and Marc'Aurelio Ranzato. 2017. Gradient episodic memory for continual learning. In NeurIPS. 6467--6476."},{"key":"e_1_3_2_2_21_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Guangyi Lv Shuai Wang Bing Liu Enhong Chen and Kun Zhang. 2019. Sentiment classification by leveraging the shared knowledge from a sequence of domains. In DASFAA . 795--811.","DOI":"10.1007\/978-3-030-18576-3_47"},{"key":"e_1_3_2_2_23_1","unstructured":"Andrew L Maas Raymond E Daly Peter T Pham Dan Huang Andrew Y Ng and Christopher Potts. 2011. Learning word vectors for sentiment analysis. In ACL. 142--150."},{"key":"e_1_3_2_2_24_1","volume-title":"Piggyback: Adapting a single network to multiple tasks by learning to mask weights. In ECCV . 67--82.","author":"Mallya Arun","year":"2018","unstructured":"Arun Mallya, Dillon Davis, and Svetlana Lazebnik. 2018. Piggyback: Adapting a single network to multiple tasks by learning to mask weights. In ECCV . 67--82."},{"key":"e_1_3_2_2_25_1","volume-title":"Packnet: Adding multiple tasks to a single network by iterative pruning. In CVPR . 7765--7773.","author":"Mallya Arun","year":"2018","unstructured":"Arun Mallya and Svetlana Lazebnik. 2018. Packnet: Adding multiple tasks to a single network by iterative pruning. In CVPR . 7765--7773."},{"key":"e_1_3_2_2_26_1","volume-title":"The stability-plasticity dilemma: Investigating the continuum from catastrophic forgetting to age-limited learning effects. Frontiers in psychology","author":"Mermillod Martial","year":"2013","unstructured":"Martial Mermillod, Aur\u00e9lia Bugaiska, and Patrick Bonin. 2013. The stability-plasticity dilemma: Investigating the continuum from catastrophic forgetting to age-limited learning effects. Frontiers in psychology , Vol. 4 (2013), 504."},{"key":"e_1_3_2_2_27_1","volume-title":"A Bayesian approach to on-line learning. On-line learning in neural networks","author":"Opper Manfred","year":"1998","unstructured":"Manfred Opper and Ole Winther. 1998. A Bayesian approach to on-line learning. On-line learning in neural networks (1998), 363--378."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Bo Pang and Lillian Lee. 2005. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. In ACL. 115--124.","DOI":"10.3115\/1219840.1219855"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"e_1_3_2_2_30_1","volume-title":"Improving language understanding by generative pre-training. Technical report at OpenAI","author":"Radford Alec","year":"2018","unstructured":"Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. Technical report at OpenAI (2018)."},{"key":"e_1_3_2_2_31_1","volume-title":"Progressive neural networks. arXiv preprint arXiv:1606.04671","author":"Rusu Andrei A","year":"2016","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_2_32_1","volume-title":"Razvan Pascanu, and Raia Hadsell.","author":"Schwarz Jonathan","year":"2018","unstructured":"Jonathan Schwarz, Jelena Luketina, Wojciech M Czarnecki, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, and Raia Hadsell. 2018. Progress & compress: A scalable framework for continual learning. arXiv preprint arXiv:1805.06370 (2018)."},{"key":"e_1_3_2_2_33_1","volume-title":"International Conference on Machine Learning . PMLR, 5986--5995","author":"Stickland Asa Cooper","year":"2019","unstructured":"Asa Cooper Stickland and Iain Murray. 2019. BERT and PALs: Projected attention layers for efficient adaptation in multi-task learning. In International Conference on Machine Learning . PMLR, 5986--5995."},{"key":"e_1_3_2_2_34_1","volume-title":"Lamol: Language modeling for lifelong language learning. arXiv preprint arXiv:1909.03329","author":"Sun Fan-Keng","year":"2019","unstructured":"Fan-Keng Sun, Cheng-Hao Ho, and Hung-Yi Lee. 2019. Lamol: Language modeling for lifelong language learning. arXiv preprint arXiv:1909.03329 (2019)."},{"key":"e_1_3_2_2_35_1","unstructured":"Kai Sheng Tai Richard Socher and Christopher D Manning. 2015. Improved semantic representations from tree-structured long short-term memory networks. In ACL. 1556--1566."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Jin Wang Liang-Chih Yu K Robert Lai and Xuejie Zhang. 2016. Dimensional sentiment analysis using a regional CNN-LSTM model. In ACL . 225--230.","DOI":"10.18653\/v1\/P16-2037"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622304"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2906098"},{"key":"e_1_3_2_2_39_1","unstructured":"Fangzhao Wu and Yongfeng Huang. 2016. Sentiment domain adaptation with multiple sources. In ACL. 301--310."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401156"},{"key":"e_1_3_2_2_41_1","volume-title":"One Model","author":"Yuan Fajie","year":"2009","unstructured":"Fajie Yuan, Guoxiao Zhang, Alexandros Karatzoglou, Xiangnan He, Joemon Jose, Beibei Kong, and Yudong Li. 2020 b. One Person, One Model, One World: Learning Continual User Representation without Forgetting. arXiv preprint arXiv:2009.13724 (2020)."},{"key":"e_1_3_2_2_42_1","first-page":"1241","article-title":"Pivot Based Language Modeling for Improved Neural Domain Adaptation","volume":"1","author":"Ziser Yftah","year":"2018","unstructured":"Yftah Ziser and Roi Reichart. 2018. Pivot Based Language Modeling for Improved Neural Domain Adaptation. In NAACL , Vol. 1. 1241--1251.","journal-title":"NAACL"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462902","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:19Z","timestamp":1750191499000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462902"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":42,"alternative-id":["10.1145\/3404835.3462902","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462902","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}