{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:27:11Z","timestamp":1783438031277,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62372209"],"award-info":[{"award-number":["62372209"]}]},{"name":"European Union’s Horizon 2020 FET Proactive Project","award":["823783"],"award-info":[{"award-number":["823783"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792237","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:28:36Z","timestamp":1777296516000},"page":"3698-3708","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9327-434X","authenticated-orcid":false,"given":"Mengyu","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8621-7144","authenticated-orcid":false,"given":"Yonghao","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5903-6150","authenticated-orcid":false,"given":"Fausto","family":"Giunchiglia","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8190-5087","authenticated-orcid":false,"given":"Ximing","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3954-1333","authenticated-orcid":false,"given":"Xiaoyue","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7162-7826","authenticated-orcid":false,"given":"Renchu","family":"Guan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AI@Meta. 2024. Llama 3 Model Card. (2024)."},{"key":"e_1_3_2_1_2_1","first-page":"770","article-title":"Deep over-sampling framework for classifying imbalanced data","author":"Ando Shin","year":"2017","unstructured":"Shin Ando and Chun Yuan Huang. 2017. Deep over-sampling framework for classifying imbalanced data. In ECMLPKDD. 770-785.","journal-title":"ECMLPKDD."},{"key":"e_1_3_2_1_3_1","first-page":"3386","article-title":"Twitter Topic Classification","author":"Antypas Dimosthenis","year":"2022","unstructured":"Dimosthenis Antypas, Asahi Ushio, Jose Camacho-Collados, V\u00edtor Silva, Leonardo Neves, and Francesco Barbieri. 2022. Twitter Topic Classification. In COLING. 3386-3400.","journal-title":"COLING."},{"key":"e_1_3_2_1_4_1","first-page":"872","article-title":"What is the effect of importance weighting in deep learning?","author":"Byrd Jonathon","year":"2019","unstructured":"Jonathon Byrd and Zachary Lipton. 2019. What is the effect of importance weighting in deep learning?. In ICML. 872-881.","journal-title":"ICML."},{"key":"e_1_3_2_1_5_1","volume-title":"Learning imbalanced datasets with label-distribution-aware margin loss. NeurIPS","author":"Cao Kaidi","year":"2019","unstructured":"Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Arechiga, and Tengyu Ma. 2019. Learning imbalanced datasets with label-distribution-aware margin loss. NeurIPS (2019)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_2_1_7_1","unstructured":"Qianben Chen Richong Zhang Yaowei Zheng and Yongyi Mao. 2024. Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation. In WWW."},{"key":"e_1_3_2_1_8_1","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In ICML. 1597-1607.","journal-title":"ICML."},{"key":"e_1_3_2_1_9_1","first-page":"9268","article-title":"Class-balanced loss based on effective number of samples","author":"Cui Yin","year":"2019","unstructured":"Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, and Serge Belongie. 2019. Class-balanced loss based on effective number of samples. In CVPR. 9268-9277.","journal-title":"CVPR."},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. In 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. In NAACL."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1341531.1341561"},{"key":"e_1_3_2_1_12_1","volume-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. arXiv preprint arXiv:2002.06305","author":"Dodge Jesse","year":"2020","unstructured":"Jesse Dodge, Gabriel Ilharco, Roy Schwartz, Ali Farhadi, Hannaneh Hajishirzi, and Noah Smith. 2020. Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping. arXiv preprint arXiv:2002.06305 (2020)."},{"key":"e_1_3_2_1_13_1","first-page":"489","article-title":"Understanding Back-Translation at Scale","author":"Edunov Sergey","year":"2018","unstructured":"Sergey Edunov, Myle Ott, Michael Auli, and David Grangier. 2018. Understanding Back-Translation at Scale. In EMNLP. 489-500.","journal-title":"EMNLP."},{"key":"e_1_3_2_1_14_1","unstructured":"Tianyu Gao Xingcheng Yao and Danqi Chen. 2021. SimCSE: Simple Contrastive Learning of Sentence Embeddings. In EMNLP."},{"key":"e_1_3_2_1_15_1","unstructured":"Beliz Gunel Jingfei Du Alexis Conneau and Veselin Stoyanov. 2021. Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning. In ICLR."},{"key":"e_1_3_2_1_16_1","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum contrast for unsupervised visual representation learning. In CVPR. 9729-9738.","journal-title":"CVPR."},{"key":"e_1_3_2_1_17_1","unstructured":"Dan Hendrycks and Thomas Dietterich. 2020. Benchmarking neural network robustness to common corruptions and perturbations. In ICLR."},{"key":"e_1_3_2_1_18_1","unstructured":"Edward J Hu Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In ICLR."},{"key":"e_1_3_2_1_19_1","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 ICML."},{"key":"e_1_3_2_1_20_1","volume-title":"NeurIPS (2020)","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. NeurIPS (2020), 18661-18673."},{"key":"e_1_3_2_1_21_1","first-page":"1746","article-title":"Convolutional Neural Networks for Sentence Classification","author":"Kim Yoon","year":"2014","unstructured":"Yoon Kim. 2014. Convolutional Neural Networks for Sentence Classification. In EMNLP. 1746-1751.","journal-title":"EMNLP."},{"key":"e_1_3_2_1_22_1","first-page":"6918","article-title":"Targeted supervised contrastive learning for long-tailed recognition","author":"Li Tianhong","year":"2022","unstructured":"Tianhong Li, Peng Cao, Yuan Yuan, Lijie Fan, Yuzhe Yang, Rogerio S Feris, Piotr Indyk, and Dina Katabi. 2022. Targeted supervised contrastive learning for long-tailed recognition. In CVPR. 6918-6928.","journal-title":"CVPR."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Xin Li and Dan Roth. 2002. Learning question classifiers. In COLING.","DOI":"10.3115\/1072228.1072378"},{"key":"e_1_3_2_1_24_1","first-page":"465","article-title":"Dice Loss for Data-imbalanced NLP Tasks","author":"Li Xiaoya","year":"2020","unstructured":"Xiaoya Li, Xiaofei Sun, Yuxian Meng, Junjun Liang, Fei Wu, and Jiwei Li. 2020. Dice Loss for Data-imbalanced NLP Tasks. In ACL. 465-476.","journal-title":"ACL."},{"key":"e_1_3_2_1_25_1","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin Tsung-Yi","year":"2017","unstructured":"Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Doll\u00e1r. 2017. Focal loss for dense object detection. In ICCV. 2980-2988.","journal-title":"ICCV."},{"key":"e_1_3_2_1_26_1","first-page":"4821","article-title":"Heterogeneous graph attention networks for semi-supervised short text classification","author":"Linmei Hu","year":"2019","unstructured":"Hu Linmei, Tianchi Yang, Chuan Shi, Houye Ji, and Xiaoli Li. 2019. Heterogeneous graph attention networks for semi-supervised short text classification. In EMNLP-IJCNLP. 4821-4830.","journal-title":"EMNLP-IJCNLP."},{"key":"e_1_3_2_1_27_1","first-page":"2326","article-title":"Multi-timescale long short-term memory neural network for modelling sentences and documents","author":"Liu Pengfei","year":"2015","unstructured":"Pengfei Liu, Xipeng Qiu, Xinchi Chen, Shiyu Wu, and Xuan-Jing Huang. 2015. Multi-timescale long short-term memory neural network for modelling sentences and documents. In EMNLP. 2326-2335.","journal-title":"EMNLP."},{"key":"e_1_3_2_1_28_1","volume-title":"Fausto Giunchiglia, Ximing Li, Sirui Wang, Wei Wu, Lan Huang, Xiaoyue Feng, and Renchu Guan.","author":"Liu Yonghao","year":"2023","unstructured":"Yonghao Liu, Mengyu Li Di Liang, Fausto Giunchiglia, Ximing Li, Sirui Wang, Wei Wu, Lan Huang, Xiaoyue Feng, and Renchu Guan. 2023. Local and Global: Temporal Question Answering via Information Fusion. In IJCAI."},{"key":"e_1_3_2_1_29_1","unstructured":"Yonghao Liu Fausto Giunchiglia Lan Huang Ximing Li Xiaoyue Feng and Renchu Guan. 2025a. A Simple Graph Contrastive Learning Framework for Short Text Classification. In AAAI."},{"key":"e_1_3_2_1_30_1","first-page":"8142","article-title":"Deep attention diffusion graph neural networks for text classification","author":"Liu Yonghao","year":"2021","unstructured":"Yonghao Liu, Renchu Guan, Fausto Giunchiglia, Yanchun Liang, and Xiaoyue Feng. 2021. Deep attention diffusion graph neural networks for text classification. In EMNLP. 8142-8152.","journal-title":"EMNLP."},{"key":"e_1_3_2_1_31_1","unstructured":"Yonghao Liu Lan Huang Fausto Giunchiglia Xiaoyue Feng and Renchu Guan. 2024. Improved Graph Contrastive Learning for Short Text Classification. In AAAI."},{"key":"e_1_3_2_1_32_1","unstructured":"Yonghao Liu Mengyu Li Wei Pang Fausto Giunchiglia Lan Huang Xiaoyue Feng and Renchu Guan. 2025b. Boosting Short Text Classification with Multi-Source Information Exploration and Dual-Level Contrastive Learning. In AAAI."},{"key":"e_1_3_2_1_33_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_34_1","volume-title":"Himanshu Jain, Andreas Veit, and Sanjiv Kumar.","author":"Menon Aditya Krishna","year":"2020","unstructured":"Aditya Krishna Menon, Sadeep Jayasumana, Ankit Singh Rawat, Himanshu Jain, Andreas Veit, and Sanjiv Kumar. 2020. Long-tail learning via logit adjustment. In ICLR."},{"key":"e_1_3_2_1_35_1","volume-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 3DV. 565-571.","author":"Milletari Fausto","year":"2016","unstructured":"Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. 2016. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 3DV. 565-571."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. In NeurIPS.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_1_37_1","unstructured":"Joshua David Robinson Ching-Yao Chuang Suvrit Sra and Stefanie Jegelka. 2020. Contrastive Learning with Hard Negative Samples. In ICLR."},{"key":"e_1_3_2_1_38_1","volume-title":"Fran\u00e7ois Yvon, et al.","author":"Scao Teven Le","year":"2022","unstructured":"Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, et al., 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Xiaohui Song Longtao Huang Hui Xue and Songlin Hu. 2022. Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation. In EMNLP.","DOI":"10.18653\/v1\/2022.emnlp-main.347"},{"key":"e_1_3_2_1_40_1","unstructured":"Sainbayar Sukhbaatar Joan Bruna Manohar Paluri Lubomir Bourdev and Rob Fergus. 2015. Training convolutional networks with noisy labels. In ICLR."},{"key":"e_1_3_2_1_41_1","first-page":"4381","article-title":"Not All Negatives are Equal","author":"Suresh Varsha","year":"2021","unstructured":"Varsha Suresh and Desmond Ong. 2021. Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification. In EMNLP. 4381-4394.","journal-title":"Label-Aware Contrastive Loss for Fine-grained Text Classification. In EMNLP."},{"key":"e_1_3_2_1_42_1","first-page":"1165","article-title":"Pte: Predictive text embedding through large-scale heterogeneous text networks","author":"Tang Jian","year":"2015","unstructured":"Jian Tang, Meng Qu, and Qiaozhu Mei. 2015. Pte: Predictive text embedding through large-scale heterogeneous text networks. In SIGKDD. 1165-1174.","journal-title":"SIGKDD."},{"key":"e_1_3_2_1_43_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"JMLR","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. JMLR, Vol. 9, 11 (2008)."},{"key":"e_1_3_2_1_45_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS."},{"key":"e_1_3_2_1_46_1","first-page":"943","article-title":"Contrastive learning based hybrid networks for long-tailed image classification","author":"Wang Peng","year":"2021","unstructured":"Peng Wang, Kai Han, Xiu-Shen Wei, Lei Zhang, and Lei Wang. 2021. Contrastive learning based hybrid networks for long-tailed image classification. In CVPR. 943-952.","journal-title":"CVPR."},{"key":"e_1_3_2_1_47_1","first-page":"6382","article-title":"EDA","author":"Wei Jason","year":"2019","unstructured":"Jason Wei and Kai Zou. 2019. EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks. In EMNLP. 6382-6388.","journal-title":"In EMNLP."},{"key":"e_1_3_2_1_48_1","unstructured":"Ziang Xie Sida I Wang Jiwei Li Daniel L\u00e9vy Aiming Nie Dan Jurafsky and Andrew Y Ng. 2017. Data noising as smoothing in neural network language models. In ICLR."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2016.12.008"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Yuzhe Yang Hao Wang and Dina Katabi. 2022. On Multi-Domain Long-Tailed Recognition Generalization and Beyond. In ECCV.","DOI":"10.1007\/978-3-031-20044-1_4"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017370"},{"key":"e_1_3_2_1_52_1","unstructured":"Hongyi Zhang Moustapha Cisse Yann N Dauphin and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In ICLR."},{"key":"e_1_3_2_1_53_1","volume-title":"Deep long-tailed learning: A survey. arXiv preprint arXiv:2110.04596","author":"Zhang Yifan","year":"2021","unstructured":"Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, and Jiashi Feng. 2021. Deep long-tailed learning: A survey. arXiv preprint arXiv:2110.04596 (2021)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Xingyu Zhao Yuexuan An Ning Xu Jing Wang and Xin Geng. 2023. Imbalanced label distribution learning. In AAAI.","DOI":"10.1609\/aaai.v37i9.26341"},{"key":"e_1_3_2_1_55_1","first-page":"6908","article-title":"Balanced contrastive learning for long-tailed visual recognition","author":"Zhu Jianggang","year":"2022","unstructured":"Jianggang Zhu, Zheng Wang, Jingjing Chen, Yi-Ping Phoebe Chen, and Yu-Gang Jiang. 2022. Balanced contrastive learning for long-tailed visual recognition. In CVPR. 6908-6917.","journal-title":"CVPR."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:50:19Z","timestamp":1783151419000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792237"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":55,"alternative-id":["10.1145\/3774904.3792237","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792237","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}