{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T07:47:37Z","timestamp":1773301657058,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":88,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"RGC Senior Research Fellow Scheme","award":["SRFS2324-2S02"],"award-info":[{"award-number":["SRFS2324-2S02"]}]},{"name":"Interdisciplinary Program of Shanghai Jiao Tong University","award":["YG2024QNB05"],"award-info":[{"award-number":["YG2024QNB05"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,28]]},"DOI":"10.1145\/3696410.3714687","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T23:08:29Z","timestamp":1745363309000},"page":"3492-3504","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Mitigating Forgetting in Adapting Pre-trained Language Models to Text Processing Tasks via Consistency Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9840-7866","authenticated-orcid":false,"given":"Jianqi","family":"Gao","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3145-044X","authenticated-orcid":false,"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7629-4648","authenticated-orcid":false,"given":"Yiu-ming","family":"Cheung","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0036-9436","authenticated-orcid":false,"given":"Jian","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3444-9992","authenticated-orcid":false,"given":"Hang","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4080-7592","authenticated-orcid":false,"given":"Yonggang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Understanding deep neural networks with rectified linear units. arXiv preprint arXiv:1611.01491","author":"Arora Raman","year":"2016","unstructured":"Raman Arora, Amitabh Basu, Poorya Mianjy, and Anirbit Mukherjee. 2016. Understanding deep neural networks with rectified linear units. arXiv preprint arXiv:1611.01491 (2016)."},{"key":"e_1_3_2_1_2_1","volume-title":"Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks. arxiv","author":"Atkinson Craig","year":"1802","unstructured":"Craig Atkinson, Brendan McCane, Lech Szymanski, and Anthony Robins. 2018. Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks. arxiv: 1802.03875 [cs.LG]"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503044"},{"key":"e_1_3_2_1_5_1","volume-title":"New insights on reducing abrupt representation change in online continual learning. arXiv preprint arXiv:2104.05025","author":"Caccia Lucas","year":"2021","unstructured":"Lucas Caccia, Rahaf Aljundi, Nader Asadi, Tinne Tuytelaars, Joelle Pineau, and Eugene Belilovsky. 2021. New insights on reducing abrupt representation change in online continual learning. arXiv preprint arXiv:2104.05025 (2021)."},{"key":"e_1_3_2_1_6_1","volume-title":"Evaluation of text generation: A survey. arXiv preprint arXiv:2006.14799","author":"Celikyilmaz Asli","year":"2020","unstructured":"Asli Celikyilmaz, Elizabeth Clark, and Jianfeng Gao. 2020. Evaluation of text generation: A survey. arXiv preprint arXiv:2006.14799 (2020)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00469"},{"key":"e_1_3_2_1_8_1","volume-title":"Efficient lifelong learning with a-gem. arXiv preprint arXiv:1812.00420","author":"Chaudhry Arslan","year":"2018","unstructured":"Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, and Mohamed Elhoseiny. 2018. Efficient lifelong learning with a-gem. arXiv preprint arXiv:1812.00420 (2018)."},{"key":"e_1_3_2_1_9_1","volume-title":"Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V Le, and Christopher D Manning. 2020. Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555 (2020)."},{"key":"e_1_3_2_1_10_1","volume-title":"Continual pre-training mitigates forgetting in language and vision. arXiv preprint arXiv:2205.09357","author":"Cossu Andrea","year":"2022","unstructured":"Andrea Cossu, Tinne Tuytelaars, Antonio Carta, Lucia Passaro, Vincenzo Lomonaco, and Davide Bacciu. 2022. Continual pre-training mitigates forgetting in language and vision. arXiv preprint arXiv:2205.09357 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_12_1","volume-title":"Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821","author":"Gao Tianyu","year":"2021","unstructured":"Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/info13020083"},{"key":"e_1_3_2_1_14_1","volume-title":"Supervised contrastive learning for pre-trained language model fine-tuning. arXiv preprint arXiv:2011.01403","author":"Gunel Beliz","year":"2020","unstructured":"Beliz Gunel, Jingfei Du, Alexis Conneau, and Ves Stoyanov. 2020. Supervised contrastive learning for pre-trained language model fine-tuning. arXiv preprint arXiv:2011.01403 (2020)."},{"key":"e_1_3_2_1_15_1","volume-title":"Don't stop pretraining: Adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964","author":"Gururangan Suchin","year":"2020","unstructured":"Suchin Gururangan, Ana Marasovi\u0107, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A Smith. 2020. Don't stop pretraining: Adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"Vanillakd: Revisit the power of vanilla knowledge distillation from small scale to large scale. arXiv preprint arXiv:2305.15781","author":"Hao Zhiwei","year":"2023","unstructured":"Zhiwei Hao, Jianyuan Guo, Kai Han, Han Hu, Chang Xu, and Yunhe Wang. 2023. Vanillakd: Revisit the power of vanilla knowledge distillation from small scale to large scale. arXiv preprint arXiv:2305.15781 (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_18_1","volume-title":"Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654","author":"He Pengcheng","year":"2020","unstructured":"Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020b. Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654 (2020)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.95"},{"key":"e_1_3_2_1_20_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_21_1","volume-title":"Classification of spam emails through hierarchical clustering and supervised learning. arXiv preprint arXiv:2005.08773","author":"J\u00e1nez-Martino Francisco","year":"2020","unstructured":"Francisco J\u00e1nez-Martino, Eduardo Fidalgo, Santiago Gonz\u00e1lez-Mart\u00ednez, and Javier Velasco-Mata. 2020. Classification of spam emails through hierarchical clustering and supervised learning. arXiv preprint arXiv:2005.08773 (2020)."},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning. PMLR, 15067--15088","author":"Jiang Xue","year":"2023","unstructured":"Xue Jiang, Feng Liu, Zhen Fang, Hong Chen, Tongliang Liu, Feng Zheng, and Bo Han. 2023. Detecting out-of-distribution data through in-distribution class prior. In International Conference on Machine Learning. PMLR, 15067--15088."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"e_1_3_2_1_24_1","volume-title":"ANNA: enhanced language representation for question answering. arXiv preprint arXiv:2203.14507","author":"Jun Changwook","year":"2022","unstructured":"Changwook Jun, Hansol Jang, Myoseop Sim, Hyun Kim, Jooyoung Choi, Kyungkoo Min, and Kyunghoon Bae. 2022. ANNA: enhanced language representation for question answering. arXiv preprint arXiv:2203.14507 (2022)."},{"key":"e_1_3_2_1_25_1","first-page":"22443","article-title":"Achieving forgetting prevention and knowledge transfer in continual learning","volume":"34","author":"Ke Zixuan","year":"2021","unstructured":"Zixuan Ke, Bing Liu, Nianzu Ma, Hu Xu, and Lei Shu. 2021. Achieving forgetting prevention and knowledge transfer in continual learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 22443--22456.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.105836"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/GCAT52182.2021.9587459"},{"key":"e_1_3_2_1_29_1","volume-title":"Dong Bok Lee, and Sung Ju Hwang","author":"Lee Seanie","year":"2020","unstructured":"Seanie Lee, Dong Bok Lee, and Sung Ju Hwang. 2020. Contrastive learning with adversarial perturbations for conditional text generation. arXiv preprint arXiv:2012.07280 (2020)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.091"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00632"},{"key":"e_1_3_2_1_32_1","volume-title":"A survey on text classification: From shallow to deep learning. arXiv preprint arXiv:2008.00364","author":"Li Qian","year":"2020","unstructured":"Qian Li, Hao Peng, Jianxin Li, Congying Xia, Renyu Yang, Lichao Sun, Philip S Yu, and Lifang He. 2020. A survey on text classification: From shallow to deep learning. arXiv preprint arXiv:2008.00364 (2020)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495162"},{"key":"e_1_3_2_1_34_1","volume-title":"Learning without forgetting","author":"Li Zhizhong","year":"2017","unstructured":"Zhizhong Li and Derek Hoiem. 2017. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 12 (2017), 2935--2947."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3115\/1118162.1118168"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-9323-9_15"},{"key":"e_1_3_2_1_38_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_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"e_1_3_2_1_41_1","volume-title":"CharBERT: character-aware pre-trained language model. arXiv preprint arXiv:2011.01513","author":"Ma Wentao","year":"2020","unstructured":"Wentao Ma, Yiming Cui, Chenglei Si, Ting Liu, Shijin Wang, and Guoping Hu. 2020. CharBERT: character-aware pre-trained language model. arXiv preprint arXiv:2011.01513 (2020)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_1_43_1","first-page":"14917","article-title":"Less-forgetting Multi-lingual Fine-tuning","volume":"35","author":"Mao Yuren","year":"2022","unstructured":"Yuren Mao, Yaobo Liang, Nan Duan, Haobo Wang, Kai Wang, Lu Chen, and Yunjun Gao. 2022. Less-forgetting Multi-lingual Fine-tuning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 14917--14928.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","volume-title":"Deep learning-based text classification: a comprehensive review. ACM computing surveys (CSUR)","author":"Minaee Shervin","year":"2021","unstructured":"Shervin Minaee, Nal Kalchbrenner, Erik Cambria, Narjes Nikzad, Meysam Chenaghlu, and Jianfeng Gao. 2021. Deep learning-based text classification: a comprehensive review. ACM computing surveys (CSUR), Vol. 54, 3 (2021), 1--40."},{"key":"e_1_3_2_1_45_1","volume-title":"How to exploit hyperspherical embeddings for out-of-distribution detection? arXiv preprint arXiv:2203.04450","author":"Ming Yifei","year":"2022","unstructured":"Yifei Ming, Yiyou Sun, Ousmane Dia, and Yixuan Li. 2022. How to exploit hyperspherical embeddings for out-of-distribution detection? arXiv preprint arXiv:2203.04450 (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"Electramed: a new pre-trained language representation model for biomedical nlp. arXiv preprint arXiv:2104.09585","author":"Miolo Giacomo","year":"2021","unstructured":"Giacomo Miolo, Giulio Mantoan, and Carlotta Orsenigo. 2021. Electramed: a new pre-trained language representation model for biomedical nlp. arXiv preprint arXiv:2104.09585 (2021)."},{"key":"e_1_3_2_1_47_1","volume-title":"Adversarial training methods for semi-supervised text classification. arXiv preprint arXiv:1605.07725","author":"Miyato Takeru","year":"2016","unstructured":"Takeru Miyato, Andrew M Dai, and Ian Goodfellow. 2016. Adversarial training methods for semi-supervised text classification. arXiv preprint arXiv:1605.07725 (2016)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.228"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1206"},{"key":"e_1_3_2_1_50_1","volume-title":"SSMBA: Self-supervised manifold based data augmentation for improving out-of-domain robustness. arXiv preprint arXiv:2009.10195","author":"Ng Nathan","year":"2020","unstructured":"Nathan Ng, Kyunghyun Cho, and Marzyeh Ghassemi. 2020. SSMBA: Self-supervised manifold based data augmentation for improving out-of-domain robustness. arXiv preprint arXiv:2009.10195 (2020)."},{"key":"e_1_3_2_1_51_1","volume-title":"DropAttack: A Random Dropped Weight Attack Adversarial Training for Natural Language Understanding","author":"Ni Shiwen","year":"2023","unstructured":"Shiwen Ni, Jiawen Li, Min Yang, and Hung-Yu Kao. 2023. DropAttack: A Random Dropped Weight Attack Adversarial Training for Natural Language Understanding. IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21362"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.03.020"},{"key":"e_1_3_2_1_55_1","volume-title":"Relative flatness and generalization. Advances in neural information processing systems","author":"Petzka Henning","year":"2021","unstructured":"Henning Petzka, Michael Kamp, Linara Adilova, Cristian Sminchisescu, and Mario Boley. 2021. Relative flatness and generalization. Advances in neural information processing systems, Vol. 34 (2021), 18420--18432."},{"key":"e_1_3_2_1_56_1","volume-title":"Improving gradient-based adversarial training for text classification by contrastive learning and auto-encoder. arXiv preprint arXiv:2109.06536","author":"Qiu Yao","year":"2021","unstructured":"Yao Qiu, Jinchao Zhang, and Jie Zhou. 2021. Improving gradient-based adversarial training for text classification by contrastive learning and auto-encoder. arXiv preprint arXiv:2109.06536 (2021)."},{"key":"e_1_3_2_1_57_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_59_1","volume-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910","author":"Riemer Matthew","year":"2018","unstructured":"Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, and Gerald Tesauro. 2018. Learning to learn without forgetting by maximizing transfer and minimizing interference. arXiv preprint arXiv:1810.11910 (2018)."},{"key":"e_1_3_2_1_60_1","volume-title":"How much knowledge can you pack into the parameters of a language model? arXiv preprint arXiv:2002.08910","author":"Roberts Adam","year":"2020","unstructured":"Adam Roberts, Colin Raffel, and Noam Shazeer. 2020. How much knowledge can you pack into the parameters of a language model? arXiv preprint arXiv:2002.08910 (2020)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1080\/09540099550039318"},{"key":"e_1_3_2_1_62_1","first-page":"123","article-title":"b","volume":"7","author":"Robins Anthony V.","year":"1995","unstructured":"Anthony V. Robins. 1995 b. Catastrophic Forgetting, Rehearsal and Pseudorehearsal. Connect. Sci., Vol. 7 (1995), 123--146. https:\/\/api.semanticscholar.org\/CorpusID:22882861","journal-title":"Catastrophic Forgetting, Rehearsal and Pseudorehearsal. Connect. Sci."},{"key":"e_1_3_2_1_63_1","volume-title":"Zheng Xu, John Dickerson, Christoph Studer, Larry S Davis, Gavin Taylor, and Tom Goldstein.","author":"Shafahi Ali","year":"2019","unstructured":"Ali Shafahi, Mahyar Najibi, Mohammad Amin Ghiasi, Zheng Xu, John Dickerson, Christoph Studer, Larry S Davis, Gavin Taylor, and Tom Goldstein. 2019. Adversarial training for free! Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_64_1","first-page":"27734","article-title":"You never cluster alone","volume":"34","author":"Shen Yuming","year":"2021","unstructured":"Yuming Shen, Ziyi Shen, Menghan Wang, Jie Qin, Philip Torr, and Ling Shao. 2021. You never cluster alone. Advances in Neural Information Processing Systems, Vol. 34 (2021), 27734--27746.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"e_1_3_2_1_66_1","volume-title":"Mice: Mixture of contrastive experts for unsupervised image clustering. arXiv preprint arXiv:2105.01899","author":"Tsai Tsung Wei","year":"2021","unstructured":"Tsung Wei Tsai, Chongxuan Li, and Jun Zhu. 2021. Mice: Mixture of contrastive experts for unsupervised image clustering. arXiv preprint arXiv:2105.01899 (2021)."},{"key":"e_1_3_2_1_67_1","volume-title":"Lisa Di Jorio, and Stan Matwin.","author":"Varno Farshid","year":"2020","unstructured":"Farshid Varno, Lucas May Petry, Lisa Di Jorio, and Stan Matwin. 2020. Learn Faster and Forget Slower via Fast and Stable Task Adaptation. arXiv preprint arXiv:2007.01388 (2020)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.11591\/csit.v1i1.pp1-12"},{"key":"e_1_3_2_1_69_1","volume-title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT. arXiv preprint arXiv:2106.02902","author":"Wallat Jonas","year":"2021","unstructured":"Jonas Wallat, Jaspreet Singh, and Avishek Anand. 2021. BERTnesia: Investigating the capture and forgetting of knowledge in BERT. arXiv preprint arXiv:2106.02902 (2021)."},{"key":"e_1_3_2_1_70_1","volume-title":"International conference on machine learning. PMLR, 9929--9939","author":"Wang Tongzhou","year":"2020","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In International conference on machine learning. PMLR, 9929--9939."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463069"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_1_73_1","volume-title":"Deepening hidden representations from pre-trained language models. arXiv preprint arXiv:1911.01940","author":"Yang Junjie","year":"2020","unstructured":"Junjie Yang and Hai Zhao. 2020. Deepening hidden representations from pre-trained language models. arXiv preprint arXiv:1911.01940 (2020)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1623"},{"key":"e_1_3_2_1_75_1","volume-title":"Prompt tuning for discriminative pre-trained language models. arXiv preprint arXiv:2205.11166","author":"Yao Yuan","year":"2022","unstructured":"Yuan Yao, Bowen Dong, Ao Zhang, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Leyu Lin, Maosong Sun, and Jianyong Wang. 2022. Prompt tuning for discriminative pre-trained language models. arXiv preprint arXiv:2205.11166 (2022)."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.323"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_38"},{"key":"e_1_3_2_1_78_1","volume-title":"CA-GNN: A Competence-Aware Graph Neural Network for Semi-Supervised Learning on Streaming Data","author":"Yu Hang","year":"2024","unstructured":"Hang Yu, Jiahao Wen, Yiping Sun, Xiao Wei, and Jie Lu. 2024. CA-GNN: A Competence-Aware Graph Neural Network for Semi-Supervised Learning on Streaming Data. IEEE Transactions on Cybernetics (2024)."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512467"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617680"},{"key":"e_1_3_2_1_81_1","volume-title":"International conference on machine learning. PMLR, 11328--11339","author":"Zhang Jingqing","year":"2020","unstructured":"Jingqing Zhang, Yao Zhao, Mohammad Saleh, and Peter Liu. 2020b. Pegasus: Pre-training with extracted gap-sentences for abstractive summarization. In International conference on machine learning. PMLR, 11328--11339."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-020-05160-8"},{"key":"e_1_3_2_1_83_1","volume-title":"Causaladv: Adversarial robustness through the lens of causality. arXiv preprint arXiv:2106.06196","author":"Zhang Yonggang","year":"2021","unstructured":"Yonggang Zhang, Mingming Gong, Tongliang Liu, Gang Niu, Xinmei Tian, Bo Han, Bernhard Sch\u00f6lkopf, and Kun Zhang. 2021a. Causaladv: Adversarial robustness through the lens of causality. arXiv preprint arXiv:2106.06196 (2021)."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2975918"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"e_1_3_2_1_86_1","volume-title":"Freelb: Enhanced adversarial training for natural language understanding. arXiv preprint arXiv:1909.11764","author":"Zhu Chen","year":"2019","unstructured":"Chen Zhu, Yu Cheng, Zhe Gan, Siqi Sun, Tom Goldstein, and Jingjing Liu. 2019. Freelb: Enhanced adversarial training for natural language understanding. arXiv preprint arXiv:1909.11764 (2019)."},{"key":"e_1_3_2_1_87_1","volume-title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding. In 8th International Conference on Learning Representations, ICLR 2020","author":"Zhu Chen","year":"2020","unstructured":"Chen Zhu, Yu Cheng, Zhe Gan, Siqi Sun, Tom Goldstein, and Jingjing Liu. 2020. FreeLB: Enhanced Adversarial Training for Natural Language Understanding. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=BygzbyHFvB"},{"key":"e_1_3_2_1_88_1","volume-title":"Learning reporting dynamics during breaking news for rumour detection in social media. arXiv preprint arXiv:1610.07363","author":"Zubiaga Arkaitz","year":"2016","unstructured":"Arkaitz Zubiaga, Maria Liakata, and Rob Procter. 2016. Learning reporting dynamics during breaking news for rumour detection in social media. arXiv preprint arXiv:1610.07363 (2016)."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714687","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:57Z","timestamp":1750295937000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714687"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":88,"alternative-id":["10.1145\/3696410.3714687","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714687","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}