{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T16:05:33Z","timestamp":1768925133151,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2019B1515130001"],"award-info":[{"award-number":["2019B1515130001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072186,61876208"],"award-info":[{"award-number":["62072186,61876208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2018B010108002"],"award-info":[{"award-number":["2018B010108002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462890","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T02:41:48Z","timestamp":1626057708000},"page":"357-366","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["StackRec"],"prefix":"10.1145","author":[{"given":"Jiachun","family":"Wang","sequence":"first","affiliation":[{"name":"South China University of Technology & Chinese Academy of Sciences, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fajie","family":"Yuan","sequence":"additional","affiliation":[{"name":"Westlake University & Tencent, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Chen","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyao","family":"Wu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Yang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Sun","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoxiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159727"},{"key":"e_1_3_2_2_2_1","volume-title":"Efficient architecture search by network transformation. arXiv preprint arXiv:1707.04873","author":"Cai Han","year":"2017","unstructured":"Han Cai, Tianyao Chen, Weinan Zhang, Yong Yu, and Jun Wang. 2017. Efficient architecture search by network transformation. arXiv preprint arXiv:1707.04873 (2017)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Lei Chen Fajie Yuan Jiaxi Yang Xiang Ao Chengming Li and Min Yang. 2021. A User-Adaptive Layer Selection Framework for Very Deep Sequential Recommender Models. (2021).","DOI":"10.1609\/aaai.v35i5.16518"},{"key":"e_1_3_2_2_4_1","volume-title":"Net2net: Accelerating learning via knowledge transfer. arXiv preprint arXiv:1511.05641","author":"Chen Tianqi","year":"2015","unstructured":"Tianqi Chen, Ian Goodfellow, and Jonathon Shlens. 2015. Net2net: Accelerating learning via knowledge transfer. arXiv preprint arXiv:1511.05641 (2015)."},{"key":"e_1_3_2_2_5_1","volume-title":"International Conference on Machine Learning. 2337--2346","author":"Gong Linyuan","year":"2019","unstructured":"Linyuan Gong, Di He, Zhuohan Li, Tao Qin, Liwei Wang, and Tieyan Liu. 2019. Efficient training of bert by progressively stacking. In International Conference on Machine Learning. 2337--2346."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080777"},{"key":"e_1_3_2_2_7_1","volume-title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. arXiv preprint arXiv:2002.02126","author":"He Xiangnan","year":"2020","unstructured":"Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, and Meng Wang. 2020. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. arXiv preprint arXiv:2002.02126 (2020)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271761"},{"key":"e_1_3_2_2_9_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_2_11_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_2_12_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_2_2_13_1","volume-title":"Shallow-to-Deep Training for Neural Machine Translation. arXiv preprint arXiv:2010.03737","author":"Li Bei","year":"2020","unstructured":"Bei Li, Ziyang Wang, Hui Liu, Yufan Jiang, Quan Du, Tong Xiao, Huizhen Wang, and Jingbo Zhu. 2020. Shallow-to-Deep Training for Neural Machine Translation. arXiv preprint arXiv:2010.03737 (2020)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132926"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109896"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556248"},{"key":"e_1_3_2_2_17_1","volume-title":"BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618","author":"Rendle Steffen","year":"2012","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2012. BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_2_19_1","volume-title":"A Generic Network Compression Framework for Sequential Recommender Systems. arXiv preprint arXiv:2004.13139","author":"Sun Yang","year":"2020","unstructured":"Yang Sun, Fajie Yuan, Ming Yang, Guoao Wei, Zhou Zhao, and Duo Liu. 2020. A Generic Network Compression Framework for Sequential Recommender Systems. arXiv preprint arXiv:2004.13139 (2020)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988452"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_2_22_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 Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357887"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412258"},{"key":"e_1_3_2_2_25_1","volume-title":"Dynamical isometry and a mean field theory of cnns: How to train 10,000-layer vanilla convolutional neural networks. arXiv preprint arXiv:1806.05393","author":"Xiao Lechao","year":"2018","unstructured":"Lechao Xiao, Yasaman Bahri, Jascha Sohl-Dickstein, Samuel S Schoenholz, and Jeffrey Pennington. 2018. Dynamical isometry and a mean field theory of cnns: How to train 10,000-layer vanilla convolutional neural networks. arXiv preprint arXiv:1806.05393 (2018)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380116"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401156"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462884"},{"key":"e_1_3_2_2_30_1","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1479--1488","author":"Zhang Yang","year":"2020","unstructured":"Yang Zhang, Fuli Feng, Chenxu Wang, Xiangnan He, Meng Wang, Yan Li, and Yongdong Zhang. 2020. How to retrain recommender system? A sequential meta-learning method. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1479--1488."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.165"},{"key":"e_1_3_2_2_32_1","volume-title":"Go Wide","author":"Zhou Denny","year":"2007","unstructured":"Denny Zhou, Mao Ye, Chen Chen, Tianjian Meng, Mingxing Tan, Xiaodan Song, Quoc Le, Qiang Liu, and Dale Schuurmans. 2020. Go Wide, Then Narrow: Efficient Training of Deep Thin Networks. arXiv preprint arXiv:2007.00811 (2020)."}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462890","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:18Z","timestamp":1750193238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462890"}},"subtitle":["Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking"],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":32,"alternative-id":["10.1145\/3404835.3462890","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462890","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}