{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T19:40:01Z","timestamp":1772826001719,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Priority Academic Program Development of Jiangsu Higher Education Institutions"},{"name":"the major project of natural science research in Universities of Jiangsu Province","award":["21KJA520004"],"award-info":[{"award-number":["21KJA520004"]}]},{"name":"NSFC","award":["61876117,62176175"],"award-info":[{"award-number":["61876117,62176175"]}]},{"name":"Suzhou Science and Technology Development Program","award":["SYC2022139"],"award-info":[{"award-number":["SYC2022139"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591679","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:23Z","timestamp":1689726143000},"page":"58-67","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Ensemble Modeling with Contrastive Knowledge Distillation for Sequential Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0486-926X","authenticated-orcid":false,"given":"Hanwen","family":"Du","sequence":"first","affiliation":[{"name":"Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7592-8925","authenticated-orcid":false,"given":"Huanhuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6721-6576","authenticated-orcid":false,"given":"Pengpeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9170-7009","authenticated-orcid":false,"given":"Fuzhen","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8980-4950","authenticated-orcid":false,"given":"Guanfeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Macquarie University, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5123-9279","authenticated-orcid":false,"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8187-6762","authenticated-orcid":false,"given":"Yanchi","family":"Liu","sequence":"additional","affiliation":[{"name":"Rutgers University, New Brunswick, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4960-174X","authenticated-orcid":false,"given":"Victor S.","family":"Sheng","sequence":"additional","affiliation":[{"name":"Texas Tech University, Lubbock, TX, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Pengguang Chen Shu Liu Hengshuang Zhao and Jiaya Jia. 2021a. Distilling Knowledge via Knowledge Review. In CVPR. 5008--5017."},{"key":"e_1_3_2_2_2_1","unstructured":"Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020b. A Simple Framework for Contrastive Learning of Visual Representations. In ICML. 1597--1607."},{"key":"e_1_3_2_2_3_1","unstructured":"Xinlei Chen Haoqi Fan Ross Girshick and Kaiming He. 2020a. Improved Baselines with Momentum Contrastive Learning. In arXiv preprint arXiv:2003.04297."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Xinlei Chen and Kaiming He. 2021. Exploring Simple Siamese Representation Learning. In CVPR. 15745--15753.","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Xinlei Chen Saining Xie and Kaiming He. 2021b. An Empirical Study of Training Self-Supervised Vision Transformers. In ICCV. 9620--9629.","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"e_1_3_2_2_6_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL. 4171--4186.","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. 4171--4186."},{"key":"e_1_3_2_2_7_1","volume-title":"Yu","author":"Fan Ziwei","year":"2022","unstructured":"Ziwei Fan, Zhiwei Liu, Yu Wang, Alice Wang, Zahra Nazari, Lei Zheng, Hao Peng, and Philip S. Yu. 2022. Sequential Recommendation via Stochastic Self-Attention. In WWW. 2036--2047."},{"key":"e_1_3_2_2_8_1","volume-title":"SEED: Self-supervised Distillation for Visual Representation. In ICLR.","author":"Fang Zhiyuan","year":"2021","unstructured":"Zhiyuan Fang, Jianfeng Wang, Lijuan Wang, Lei Zhang, Yezhou Yang, and Zicheng Liu. 2021. SEED: Self-supervised Distillation for Visual Representation. In ICLR."},{"key":"e_1_3_2_2_9_1","unstructured":"Tianyu Gao Xingcheng Yao and Danqi Chen. 2021. SimCSE: Simple Contrastive Learning of Sentence Embeddings. In EMNLP. 6894--6910."},{"key":"e_1_3_2_2_10_1","unstructured":"Timur Garipov Pavel Izmailov Dmitrii Podoprikhin Dmitry P Vetrov and Andrew G Wilson. 2018. Loss Surfaces Mode Connectivity and Fast Ensembling of DNNs. In NeurIPS. 8803--8812."},{"key":"e_1_3_2_2_11_1","volume-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels. In NeurIPS. 8536--8546.","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor W. Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. In NeurIPS. 8536--8546."},{"key":"e_1_3_2_2_12_1","volume-title":"Konstan","author":"Maxwell Harper F.","year":"2015","unstructured":"F. Maxwell Harper and Joseph A. Konstan. 2015. The MovieLens Datasets: History and Context. ACM Trans. Interact. Intell. Syst. (2015), 1--19."},{"key":"e_1_3_2_2_13_1","unstructured":"Kaiming He Haoqi Fan Yuxin Wu Saining Xie and Ross Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In CVPR. 9726--9735."},{"key":"e_1_3_2_2_14_1","unstructured":"Ruining He and Julian McAuley. 2016. Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation. In ICDM. 191--200."},{"key":"e_1_3_2_2_15_1","unstructured":"Bal\u00e1 zs Hidasi Alexandros Karatzoglou Linas Baltrunas and Domonkos Tikk. 2016. Session-based Recommendations with Recurrent Neural Networks. ICLR."},{"key":"e_1_3_2_2_16_1","volume-title":"Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_17_1","volume-title":"Weinberger","author":"Huang Gao","year":"2017","unstructured":"Gao Huang, Yixuan Li, Geoff Pleiss, Zhuang Liu, John E. Hopcroft, and Kilian Q. Weinberger. 2017. Snapshot Ensembles: Train 1, Get M for Free. In ICLR."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Wang-Cheng Kang and Julian McAuley. 2018. Self-Attentive Sequential Recommendation. In ICDM. 197--206.","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_2_19_1","unstructured":"Kenji Kawaguchi. 2016. Deep Learning without Poor Local Minima. In NeurIPS. 586--594."},{"key":"e_1_3_2_2_20_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Walid Krichene and Steffen Rendle. 2020. On Sampled Metrics for Item Recommendation. In SIGKDD. 1748--1757.","DOI":"10.1145\/3394486.3403226"},{"key":"e_1_3_2_2_22_1","unstructured":"Xu Lan Xiatian Zhu and Shaogang Gong. 2018. Knowledge Distillation by On-the-Fly Native Ensemble. In NeurIPS. 7528--7538."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Julian McAuley Christopher Targett Javen Shi and Anton van den Hengel. 2015. Image-based Recommendations on Styles and Substitutes. In SIGIR. 43--52.","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_2_24_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In NeurIPS. 8024--8035."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Ruihong Qiu Zi Huang and Hongzhi Yin. 2021. Memory Augmented Multi-Instance Contrastive Predictive Coding for Sequential Recommendation. In ICDM. 519--528.","DOI":"10.1109\/ICDM51629.2021.00063"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Ruihong Qiu Zi Huang Hongzhi Yin and Zijian Wang. 2022. Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation. In WSDM. 813--823.","DOI":"10.1145\/3488560.3498433"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Steffen Rendle Christoph Freudenthaler and Lars Schmidt-Thieme. 2010. Factorizing personalized Markov chains for next-basket recommendation. In WWW. 811--820.","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_2_28_1","unstructured":"Guy Shani Ronen I. Brafman and David Heckerman. 2005. An MDP-Based Recommender System. JMLR 1265--1295."},{"key":"e_1_3_2_2_29_1","unstructured":"Guocong Song and Wei Chai. 2018. Collaborative Learning for Deep Neural Networks. In NeurIPS. 1837--1846."},{"key":"e_1_3_2_2_30_1","volume-title":"JMLR (2014)","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. JMLR (2014), 1929--1958."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Fei Sun Jun Liu Jian Wu Changhua Pei Xiao Lin Wenwu Ou and Peng Jiang. 2019. BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer. In CIKM. 1441--1450.","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Jiaxi Tang and Ke Wang. 2018. Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding. In WSDM. 565--573.","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_2_33_1","unstructured":"Yonglong Tian Dilip Krishnan and Phillip Isola. 2020. Contrastive Representation Distillation. In ICLR."},{"key":"e_1_3_2_2_34_1","unstructured":"Florian Tram\u00e8r Alexey Kurakin Nicolas Papernot Ian Goodfellow Dan Boneh and Patrick McDaniel. 2018. Ensemble Adversarial Training: Attacks and Defenses. In ICLR."},{"key":"e_1_3_2_2_35_1","volume-title":"Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748","author":"van den Oord A\u00e4ron","year":"2018","unstructured":"A\u00e4ron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_2_36_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. 6000--6010."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Feng Wang and Huaping Liu. 2021. Understanding the Behaviour of Contrastive Loss. In CVPR. 2495--2504.","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"e_1_3_2_2_38_1","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding Contrastive Representation Learning Through Alignment and Uniformity on the Hypersphere. In ICML. 9929--9939."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Wei Wei Chao Huang Lianghao Xia Yong Xu Jiashu Zhao and Dawei Yin. 2022. Contrastive Meta Learning with Behavior Multiplicity for Recommendation. In WSDM. 1120--1128.","DOI":"10.1145\/3488560.3498527"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Xu Xie Fei Sun Zhaoyang Liu Shiwen Wu Jinyang Gao Jiandong Zhang Bolin Ding and Bin Cui. 2022. Contrastive Learning for Sequential Recommendation. In ICDE. 1259--1273.","DOI":"10.1109\/ICDE53745.2022.00099"},{"key":"e_1_3_2_2_41_1","unstructured":"Yuanmeng Yan Rumei Li Sirui Wang Fuzheng Zhang Wei Wu and Weiran Xu. 2021. ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer. In ACL. 5065--5075."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Junliang Yu Hongzhi Yin Xin Xia Tong Chen Lizhen Cui and Quoc Viet Hung Nguyen. 2022. Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation. In SIGIR. 1294--1303.","DOI":"10.1145\/3477495.3531937"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Tingting Zhang Pengpeng Zhao Yanchi Liu Victor S. Sheng Jiajie Xu Deqing Wang Guanfeng Liu and Xiaofang Zhou. 2019. Feature-level Deeper Self-Attention Network for Sequential Recommendation. In IJCAI. 4320--4326.","DOI":"10.24963\/ijcai.2019\/600"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Ying Zhang Tao Xiang Timothy M. Hospedales and Huchuan Lu. 2018. Deep Mutual Learning. In CVPR. 4320--4328.","DOI":"10.1109\/CVPR.2018.00454"},{"key":"e_1_3_2_2_45_1","volume-title":"Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, and Ji-Rong Wen.","author":"Zhou Kun","year":"2020","unstructured":"Kun Zhou, Hui Wang, Wayne Xin Zhao, Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, and Ji-Rong Wen. 2020. S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization. In CIKM. 1893--1902."}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591679","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:40Z","timestamp":1750182700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591679"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":45,"alternative-id":["10.1145\/3539618.3591679","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591679","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}