{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T09:02:20Z","timestamp":1775206940261,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":37,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. U23B2056"],"award-info":[{"award-number":["No. U23B2056"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0120203"],"award-info":[{"award-number":["2022ZD0120203"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Funds of the Zhejiang Provincial Natural Science Foundation of China","award":["No. LGG22F020043"],"award-info":[{"award-number":["No. LGG22F020043"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,28]]},"DOI":"10.1145\/3696410.3714797","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T23:08:29Z","timestamp":1745363309000},"page":"3300-3310","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Preserving Label Correlation for Multi-label Text Classification by Prototypical Regularizations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9046-740X","authenticated-orcid":false,"given":"Fanshuang","family":"Kong","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1207-0300","authenticated-orcid":false,"given":"Richong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8851-4211","authenticated-orcid":false,"given":"Xiaohui","family":"Guo","sequence":"additional","affiliation":[{"name":"China Software Testing Center, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6807-0089","authenticated-orcid":false,"given":"Junfan","family":"Chen","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0504-4830","authenticated-orcid":false,"given":"Ziqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100378"},{"key":"e_1_3_2_1_2_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_1_3_1","volume-title":"international conference on machine learning. PMLR, 1383--1398","author":"Bai Junwen","year":"2022","unstructured":"Junwen Bai, Shufeng Kong, and Carla P Gomes. 2022. Gaussian mixture variational autoencoder with contrastive learning for multi-label classification. In international conference on machine learning. PMLR, 1383--1398."},{"key":"e_1_3_2_1_4_1","volume-title":"Ranking-Based Autoencoder for Extreme Multi-label Classification. arXiv preprint arXiv:1904.05937","author":"Bingyu W","year":"2019","unstructured":"W Bingyu, L Chen, W Sun, K Qin, K Li, and H Zhou. 2019. Ranking-Based Autoencoder for Extreme Multi-label Classification. arXiv preprint arXiv:1904.05937 (2019)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557011"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016359"},{"key":"e_1_3_2_1_7_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Augmenting Data with Mixup for Sentence Classification: An Empirical Study. CoRR","author":"Guo Hongyu","year":"2019","unstructured":"Hongyu Guo, Yongyi Mao, and Richong Zhang. 2019a. Augmenting Data with Mixup for Sentence Classification: An Empirical Study. CoRR, Vol. abs\/1905.08941 (2019). arXiv:1905.08941 http:\/\/arxiv.org\/abs\/1905.08941"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013714"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20641"},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.731"},{"key":"e_1_3_2_1_13_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/478"},{"key":"e_1_3_2_1_15_1","volume-title":"A simple weight decay can improve generalization. Advances in neural information processing systems","author":"Krogh Anders","year":"1991","unstructured":"Anders Krogh and John Hertz. 1991. A simple weight decay can improve generalization. Advances in neural information processing systems, Vol. 4 (1991)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/1005332.1005345"},{"key":"e_1_3_2_1_17_1","volume-title":"Visualizing the loss landscape of neural nets. Advances in neural information processing systems","author":"Li Hao","year":"2018","unstructured":"Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, and Tom Goldstein. 2018. Visualizing the loss landscape of neural nets. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_18_1","volume-title":"Label supervised llama finetuning. arXiv preprint arXiv:2310.01208","author":"Li Zongxi","year":"2023","unstructured":"Zongxi Li, Xianming Li, Yuzhang Liu, Haoran Xie, Jing Li, Fu-lee Wang, Qing Li, and Xiaoqin Zhong. 2023. Label supervised llama finetuning. arXiv preprint arXiv:2310.01208 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080834"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87481-2_4"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.298"},{"key":"e_1_3_2_1_22_1","volume-title":"Chatgpt: Optimizing language models for dialogue. https:\/\/openai.com\/blog\/chatgpt.","author":"AI.","year":"2022","unstructured":"OpenAI. 2022. Chatgpt: Optimizing language models for dialogue. https:\/\/openai.com\/blog\/chatgpt."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671754"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_25_1","volume-title":"Prototypical networks for few-shot learning. Advances in neural information processing systems","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, Vol. 15, 1 (2014), 1929--1958."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning. 6438--6447","author":"Verma Vikas","year":"2019","unstructured":"Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. 2019. Manifold Mixup: Better Representations by Interpolating Hidden States. In Proceedings of the 36th International Conference on Machine Learning. 6438--6447."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 672--679","author":"Wang Ran","year":"2022","unstructured":"Ran Wang, Xinyu Dai, et al. 2022. Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text Classification. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 672--679."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1044"},{"key":"e_1_3_2_1_30_1","volume-title":"Does head label help for long-tailed multi-label text classification. arXiv preprint arXiv:2101.09704","author":"Xiao Lin","year":"2021","unstructured":"Lin Xiao, Xiangliang Zhang, Liping Jing, Chi Huang, and Mingyang Song. 2021. Does head label help for long-tailed multi-label text classification. arXiv preprint arXiv:2101.09704 (2021)."},{"key":"e_1_3_2_1_31_1","volume-title":"SGM: sequence generation model for multi-label classification. arXiv preprint arXiv:1806.04822","author":"Yang Pengcheng","year":"2018","unstructured":"Pengcheng Yang, Xu Sun, Wei Li, Shuming Ma, Wei Wu, and Houfeng Wang. 2018. SGM: sequence generation model for multi-label classification. arXiv preprint arXiv:1806.04822 (2018)."},{"key":"e_1_3_2_1_32_1","volume-title":"Prototypical networks for multi-label learning. arXiv preprint arXiv:1911.07203","author":"Yang Zhuo","year":"2019","unstructured":"Zhuo Yang, Yufei Han, Guoxian Yu, Qiang Yang, and Xiangliang Zhang. 2019. Prototypical networks for multi-label learning. arXiv preprint arXiv:1911.07203 (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"You Ronghui","year":"2019","unstructured":"Ronghui You, Zihan Zhang, Ziye Wang, Suyang Dai, Hiroshi Mamitsuka, and Shanfeng Zhu. 2019. Attentionxml: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Learning Representations.","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2018a. mixup: Beyond Empirical Risk Minimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Qian-Wen Zhang Ximing Zhang Zhao Yan Ruifang Liu Yunbo Cao and Min-Ling Zhang. 2021. Correlation-Guided Representation for Multi-Label Text Classification.. In IJCAI. 3363--3369.","DOI":"10.24963\/ijcai.2021\/463"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206030"},{"key":"e_1_3_2_1_37_1","volume-title":"Variational Continuous Label Distribution Learning for Multi-Label Text Classification","author":"Zhao Xingyu","year":"2023","unstructured":"Xingyu Zhao, Yuexuan An, Ning Xu, and Xin Geng. 2023. Variational Continuous Label Distribution Learning for Multi-Label Text Classification. IEEE Transactions on Knowledge and Data Engineering (2023)."}],"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\/3696410.3714797","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:42Z","timestamp":1750295922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":37,"alternative-id":["10.1145\/3696410.3714797","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714797","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"}}]}}