{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:26:45Z","timestamp":1765499205553,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761294","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:59:18Z","timestamp":1762559958000},"page":"3123-3132","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Transformers are Good Clusterers for Lifelong User Behavior Sequence Modeling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7821-4638","authenticated-orcid":false,"given":"Xingmei","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1567-8012","authenticated-orcid":false,"given":"Shiyao","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8789-2319","authenticated-orcid":false,"given":"Wuchao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1274-4154","authenticated-orcid":false,"given":"Jiaxin","family":"Deng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0848-1391","authenticated-orcid":false,"given":"Song","family":"Lu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3507-9607","authenticated-orcid":false,"given":"Defu","family":"Lian","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8550-279X","authenticated-orcid":false,"given":"Guorui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1109\/ICCIMA.2007.328"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1016\/j.patcog.2022.109144"},{"key":"e_1_3_2_1_3_1","first-page":"2974","article-title":"Sampling is all you need on modeling long-term user behaviors for CTR prediction","author":"Cao Yue","year":"2022","unstructured":"Yue Cao, Xiaojiang Zhou, Jiaqi Feng, Peihao Huang, Yao Xiao, Dayao Chen, and Sheng Chen. 2022. Sampling is all you need on modeling long-term user behaviors for CTR prediction. In CIKM. 2974-2983.","journal-title":"CIKM."},{"key":"e_1_3_2_1_4_1","first-page":"3785","article-title":"TWIN: TWo-stage interest network for lifelong user behavior modeling in CTR prediction at kuaishou","author":"Chang Jianxin","year":"2023","unstructured":"Jianxin Chang, Chenbin Zhang, Zhiyi Fu, Xiaoxue Zang, Lin Guan, Jing Lu, Yiqun Hui, Dewei Leng, Yanan Niu, Yang Song, et al., 2023. TWIN: TWo-stage interest network for lifelong user behavior modeling in CTR prediction at kuaishou. In KDD. 3785-3794.","journal-title":"KDD."},{"key":"e_1_3_2_1_5_1","volume-title":"End-to-end user behavior retrieval in click-through rateprediction model. arXiv preprint arXiv:2108.04468","author":"Chen Qiwei","year":"2021","unstructured":"Qiwei Chen, Changhua Pei, Shanshan Lv, Chao Li, Junfeng Ge, and Wenwu Ou. 2021. End-to-end user behavior retrieval in click-through rateprediction model. arXiv preprint arXiv:2108.04468 (2021)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1145\/3326937.3341261"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1145\/2988450.2988454"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1145\/2959100.2959190"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1145\/3637528.3671511"},{"key":"e_1_3_2_1_10_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. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1007\/978-981-15-1209-4_1"},{"key":"e_1_3_2_1_12_1","first-page":"38912","article-title":"Recommender forest for efficient retrieval","volume":"35","author":"Feng Chao","year":"2022","unstructured":"Chao Feng, Wuchao Li, Defu Lian, Zheng Liu, and Enhong Chen. 2022. Recommender forest for efficient retrieval. Advances in Neural Information Processing Systems, Vol. 35 (2022), 38912-38924.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","volume-title":"Deep session interest network for click-through rate prediction. arXiv preprint arXiv:1905.06482","author":"Feng Yufei","year":"2019","unstructured":"Yufei Feng, Fuyu Lv, Weichen Shen, Menghan Wang, Fei Sun, Yu Zhu, and Keping Yang. 2019. Deep session interest network for click-through rate prediction. arXiv preprint arXiv:1905.06482 (2019)."},{"unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. In IJCAI.","key":"e_1_3_2_1_14_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1109\/CVPR52688.2022.01553"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1145\/3298689.3347043"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1109\/ICDM.2018.00035"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.3390\/electronics11010141"},{"doi-asserted-by":"crossref","unstructured":"Doyup Lee Chiheon Kim Saehoon Kim Minsu Cho and Wook-Shin Han. 2022. Autoregressive image generation using residual quantization. In CVPR.","key":"e_1_3_2_1_19_1","DOI":"10.1109\/CVPR52688.2022.01123"},{"unstructured":"Wuchao Li Chao Feng Defu Lian Yuxin Xie Haifeng Liu Yong Ge and Enhong Chen. 2023. Learning balanced tree indexes for large-scale vector retrieval. In KDD.","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","first-page":"6252","article-title":"MixMAE: Mixed and masked autoencoder for efficient pretraining of hierarchical vision transformers","author":"Liu Jihao","year":"2023","unstructured":"Jihao Liu, Xin Huang, Jinliang Zheng, Yu Liu, and Hongsheng Li. 2023b. MixMAE: Mixed and masked autoencoder for efficient pretraining of hierarchical vision transformers. In CVPR. 6252-6261.","journal-title":"CVPR."},{"unstructured":"Qi Liu Xuyang Hou Haoran Jin Zhe Wang Defu Lian Tan Qu Jia Cheng Jun Lei et al. 2023a. Deep Group Interest Modeling of Full Lifelong User Behaviors for CTR Prediction. arXiv preprint arXiv:2311.10764 (2023).","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","volume-title":"QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou. arXiv preprint arXiv:2411.11739","author":"Luo Xinchen","year":"2024","unstructured":"Xinchen Luo, Jiangxia Cao, Tianyu Sun, Jinkai Yu, Rui Huang, Wei Yuan, Hezheng Lin, Yichen Zheng, Shiyao Wang, Qigen Hu, et al., 2024. QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou. arXiv preprint arXiv:2411.11739 (2024)."},{"unstructured":"Kelong Mao Jieming Zhu Liangcai Su Guohao Cai Yuru Li and Zhenhua Dong. 2023. FinalMLP: an enhanced two-stream MLP model for CTR prediction. In AAAI.","key":"e_1_3_2_1_24_1"},{"key":"e_1_3_2_1_25_1","volume-title":"Chi Nhan Duong, Tien D. Bui, and Khoa Luu.","author":"Nguyen Xuan-Bac","year":"2021","unstructured":"Xuan-Bac Nguyen, Duc Toan Bui, Chi Nhan Duong, Tien D. Bui, and Khoa Luu. 2021. Clusformer: A Transformer Based Clustering Approach to Unsupervised Large-Scale Face and Visual Landmark Recognition. In CVPR."},{"key":"e_1_3_2_1_26_1","first-page":"2671","article-title":"Practice on long sequential user behavior modeling for click-through rate prediction","author":"Pi Qi","year":"2019","unstructured":"Qi Pi, Weijie Bian, Guorui Zhou, Xiaoqiang Zhu, and Kun Gai. 2019. Practice on long sequential user behavior modeling for click-through rate prediction. In KDD. 2671-2679.","journal-title":"KDD."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1145\/3340531.3412744"},{"unstructured":"Jiarui Qin Weinan Zhang Xin Wu Jiarui Jin Yuchen Fang and Yong Yu. 2020. User behavior retrieval for click-through rate prediction. In SIGIR.","key":"e_1_3_2_1_28_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1109\/ICDM.2016.0151"},{"unstructured":"Alec Radford. 2018. Improving language understanding by generative pre-training. (2018).","key":"e_1_3_2_1_30_1"},{"doi-asserted-by":"crossref","unstructured":"Steffen Rendle. 2010. Factorization machines. In ICDM.","key":"e_1_3_2_1_31_1","DOI":"10.1109\/ICDM.2010.127"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1109\/DSAA49011.2020.00096"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1145\/3627673.3680030"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1145\/3357384.3357925"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_36_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_37_1","volume-title":"Attention is all you need. NeurIPS","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. NeurIPS (2017)."},{"key":"e_1_3_2_1_38_1","first-page":"2390","article-title":"ClusterFormer","author":"Wang Ningning","year":"2022","unstructured":"Ningning Wang, Guobing Gan, Peng Zhang, Shuai Zhang, Victor Junqiu Wei, Qun Liu, and Xin Jiang. 2022. ClusterFormer: Neural Clustering Attention for Efficient and Effective Transformer. In ACL. 2390-2402.","journal-title":"Neural Clustering Attention for Efficient and Effective Transformer. In ACL."},{"doi-asserted-by":"crossref","unstructured":"Ruoxi Wang Bin Fu Gang Fu and Mingliang Wang. 2017. Deep & cross network for ad click predictions. In ADKDD.","key":"e_1_3_2_1_39_1","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_1_40_1","volume-title":"Chi","author":"Wang Ruoxi","year":"2021","unstructured":"Ruoxi Wang, Rakesh Shivanna, Derek Cheng, Sagar Jain, Dong Lin, Lichan Hong, and Ed Chi. 2021. Dcn v2: Improved deep & cross network and practical lessons for web-scale learning to rank systems. In WWWW."},{"key":"e_1_3_2_1_41_1","volume-title":"RetroMAE: Pre-training retrieval-oriented language models via masked auto-encoder. arXiv preprint arXiv:2205.12035","author":"Xiao Shitao","year":"2022","unstructured":"Shitao Xiao, Zheng Liu, Yingxia Shao, and Zhao Cao. 2022. RetroMAE: Pre-training retrieval-oriented language models via masked auto-encoder. arXiv preprint arXiv:2205.12035 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction. arXiv preprint arXiv:2411.15005","author":"Xu Xiang","year":"2024","unstructured":"Xiang Xu, Hao Wang, Wei Guo, Luankang Zhang, Wanshan Yang, Runlong Yu, Yong Liu, Defu Lian, and Enhong Chen. 2024. Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction. arXiv preprint arXiv:2411.15005 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_43_1","DOI":"10.1145\/3459637.3482088"},{"key":"e_1_3_2_1_44_1","volume-title":"Neural Networks","volume":"121","author":"Yang Yi","year":"2020","unstructured":"Yi Yang, Baile Xu, Shaofeng Shen, Furao Shen, and Jian Zhao. 2020. Operation-aware neural networks for user response prediction. Neural Networks, Vol. 121 (2020)."},{"key":"e_1_3_2_1_45_1","volume-title":"Defu Lian, Xing Xie, and Wei-Ying Ma.","author":"Zhang Fuzheng","year":"2016","unstructured":"Fuzheng Zhang, Nicholas Jing Yuan, Defu Lian, Xing Xie, and Wei-Ying Ma. 2016. Collaborative knowledge base embedding for recommender systems. In KDD."},{"key":"e_1_3_2_1_46_1","volume-title":"How mask matters: Towards theoretical understandings of masked autoencoders. NeurIPS","author":"Zhang Qi","year":"2022","unstructured":"Qi Zhang, Yifei Wang, and Yisen Wang. 2022. How mask matters: Towards theoretical understandings of masked autoencoders. NeurIPS (2022)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_47_1","DOI":"10.1609\/aaai.v33i01.33015941"},{"doi-asserted-by":"crossref","unstructured":"Guorui Zhou Xiaoqiang Zhu Chenru Song Ying Fan Han Zhu Xiao Ma Yanghui Yan Junqi Jin Han Li and Kun Gai. 2018. Deep interest network for click-through rate prediction. In KDD.","key":"e_1_3_2_1_48_1","DOI":"10.1145\/3219819.3219823"}],"event":{"sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"acronym":"CIKM '25","name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:22:22Z","timestamp":1765498942000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761294"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":48,"alternative-id":["10.1145\/3746252.3761294","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761294","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}