{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:42:34Z","timestamp":1778812954119,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737117","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:07:39Z","timestamp":1754255259000},"page":"2893-2903","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Scaling Transformers for Discriminative Recommendation via Generative Pretraining"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8047-0867","authenticated-orcid":false,"given":"Chunqi","family":"Wang","sequence":"first","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8164-4240","authenticated-orcid":false,"given":"Bingchao","family":"Wu","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4871-848X","authenticated-orcid":false,"given":"Zheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5249-7037","authenticated-orcid":false,"given":"Lei","family":"Shen","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7976-8642","authenticated-orcid":false,"given":"Bing","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3742-4910","authenticated-orcid":false,"given":"Xiaoyi","family":"Zeng","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Newsha Ardalani Carole-Jean Wu Zeliang Chen Bhargav Bhushanam and Adnan Aziz. 2022. Understanding scaling laws for recommendation models. arXiv preprint arXiv:2208.08489(2022)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341261"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_2_4_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929(2020)."},{"key":"e_1_3_2_2_5_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_2_6_1","unstructured":"Zhongxiang Fan Zhaocheng Liu Jian Liang Dongying Kong Han Li Peng Jiang Shuang Li and Kun Gai. 2024. Multi-Epoch learning with Data Augmentation for Deep Click-Through Rate Prediction. arXiv preprint arXiv:2407.01607(2024)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481953"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412697"},{"key":"e_1_3_2_2_9_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247(2017)."},{"key":"e_1_3_2_2_10_1","unstructured":"Xingzhuo Guo Junwei Pan Ximei Wang Baixu Chen Jie Jiang and Mingsheng Long. 2023. On the Embedding Collapse when Scaling up Recommendation Models. arXiv preprint arXiv:2310.04400(2023)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679914"},{"key":"e_1_3_2_2_12_1","unstructured":"B Hidasi. 2015. Session-based Recommendations with Recurrent Neural Networks. arXiv preprint arXiv:1511.06939(2015)."},{"key":"e_1_3_2_2_13_1","unstructured":"S\u00e9bastien Jean Kyunghyun Cho Roland Memisevic and Yoshua Bengio. 2014. On using very large target vocabulary for neural machine translation. arXiv preprint arXiv:1412.2007(2014)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_2_15_1","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361(2020)."},{"key":"e_1_3_2_2_16_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437(2024)."},{"key":"e_1_3_2_2_17_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. arxiv:1711.05101 [cs.LG] https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5346"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533727"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330666"},{"key":"e_1_3_2_2_21_1","first-page":"606","article-title":"Efficiently scaling transformer inference","volume":"5","author":"Pope Reiner","year":"2023","unstructured":"Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Jonathan Heek, Kefan Xiao, Shivani Agrawal, and Jeff Dean. 2023. Efficiently scaling transformer inference. Proceedings of Machine Learning and Systems, Vol. 5 (2023), 606-624.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_2_22_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_2_23_1","unstructured":"Noam Shazeer. 2020. Glu variants improve transformer. arXiv preprint arXiv:2002.05202(2020)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25582"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_2_28_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971(2023).","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971(2023)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637061"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412092"},{"key":"e_1_3_2_2_32_1","volume-title":"International Conference on Machine Learning. PMLR, 10524-10533","author":"Xiong Ruibin","year":"2020","unstructured":"Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tieyan Liu. 2020. On layer normalization in the transformer architecture. In International Conference on Machine Learning. PMLR, 10524-10533."},{"key":"e_1_3_2_2_33_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115(2024)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401156"},{"key":"e_1_3_2_2_35_1","unstructured":"Jiaqi Zhai Lucy Liao Xing Liu Yueming Wang Rui Li Xuan Cao Leon Gao Zhaojie Gong Fangda Gu Michael He et al. 2024. Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations. arXiv preprint arXiv:2402.17152(2024)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"e_1_3_2_2_37_1","volume-title":"Wukong: Towards a Scaling Law for Large-Scale Recommendation. arXiv preprint arXiv:2403.02545(2024).","author":"Zhang Buyun","year":"2024","unstructured":"Buyun Zhang, Liang Luo, Yuxin Chen, Jade Nie, Xi Liu, Daifeng Guo, Yanli Zhao, Shen Li, Yuchen Hao, Yantao Yao, et al., 2024b. Wukong: Towards a Scaling Law for Large-Scale Recommendation. arXiv preprint arXiv:2403.02545(2024)."},{"key":"e_1_3_2_2_38_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Zhang Biao","year":"2019","unstructured":"Biao Zhang and Rico Sennrich. 2019. Root mean square layer normalization. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688129"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557479"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:08:53Z","timestamp":1777572533000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":42,"alternative-id":["10.1145\/3711896.3737117","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737117","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}