{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T22:46:01Z","timestamp":1777675561153,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":36,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462936","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T03:08:25Z","timestamp":1626059305000},"page":"1279-1287","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Looking at CTR Prediction Again: Is Attention All You Need?"],"prefix":"10.1145","author":[{"given":"Yuan","family":"Cheng","sequence":"first","affiliation":[{"name":"Career Science Lab, BOSS Zhipin, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbo","family":"Xue","sequence":"additional","affiliation":[{"name":"Career Science Lab, BOSS Zhipin, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the 22nd National Conference on Artificial Intelligence -","volume":"2","author":"Becker Hila","year":"2007","unstructured":"Hila Becker, Christopher Meek, and David Maxwell Chickering. 2007. Modeling Contextual Factors of Click Rates. In Proceedings of the 22nd National Conference on Artificial Intelligence - Volume 2 (Vancouver, British Columbia, Canada) (AAAI'07). AAAI Press, 1310--1315."},{"key":"e_1_3_2_2_2_1","volume-title":"Higher-Order Factorization Machines (NIPS'16","author":"Blondel Mathieu","year":"2016","unstructured":"Mathieu Blondel, Akinori Fujino, Naonori Ueda, and Masakazu Ishihata. 2016. Higher-Order Factorization Machines (NIPS'16, Vol. 29). Curran Associates Inc., Red Hook, NY, USA, 3359--3367. https:\/\/proceedings.neurips.cc\/paper\/2016\/file\/158fc2ddd52ec2cf54d3c161f2dd6517-Paper.pdf"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347058"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835671"},{"key":"e_1_3_2_2_6_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. north american","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Mingwei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. north american chapter of the association for computational linguistics (2018)."},{"key":"e_1_3_2_2_7_1","first-page":"203","article-title":"Bounded rationality: The adaptive toolbox","volume":"35","author":"Gigerenzer Gerd","year":"2000","unstructured":"Gerd Gigerenzer and Reinhard Selten. 2000. Bounded rationality: The adaptive toolbox. International Journal of Psychology, Vol. 35 (2000), 203--204.","journal-title":"International Journal of Psychology"},{"key":"e_1_3_2_2_8_1","volume-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks., Vol. 9 (13--15 May 2010), 249--256. http:\/\/proceedings.mlr.press\/v9\/glorot10a.html"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172127"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080777"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3415959.3416001"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959134"},{"key":"e_1_3_2_2_14_1","volume-title":"Adam: A Method for Stochastic Optimization.","author":"Kingma D.P","year":"2015","unstructured":"D.P Kingma and L.J. Ba. 2015. Adam: A Method for Stochastic Optimization."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","unstructured":"Malte Ludewig Noemi Mauro Sara Latifi and Dietmar Jannach. 2019. Performance comparison of neural and non-neural approaches to session-based recommendation. (2019) 462--466. https:\/\/doi.org\/10.1145\/3298689.3347041","DOI":"10.1145\/3298689.3347041"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488200"},{"key":"e_1_3_2_2_19_1","volume-title":"Hao-Jun Michael Shi, et al","author":"Naumov Maxim","year":"2019","unstructured":"Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, et al. 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 (2019)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186040"},{"key":"e_1_3_2_2_21_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0151"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2168752.2168771"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010002"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","unstructured":"Steffen Rendle Walid Krichene Li Zhang and John Anderson. 2020. Neural Collaborative Filtering vs. Matrix Factorization Revisited. (2020) 240--248. https:\/\/doi.org\/10.1145\/3383313.3412488","DOI":"10.1145\/3383313.3412488"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242643"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939704"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_2_2_31_1","volume-title":"Discrete choice methods with simulation","author":"Train Kenneth E","unstructured":"Kenneth E Train. 2009a. Discrete choice methods with simulation .Cambridge university press."},{"key":"e_1_3_2_2_32_1","first-page":"54","article-title":"Discrete Choice Methods with Simulation: Properties of Discrete Choice Models","volume":"10","author":"Train Kenneth E","year":"2009","unstructured":"Kenneth E Train. 2009b. Discrete Choice Methods with Simulation: Properties of Discrete Choice Models. Econometric Reviews, Vol. 10, 4 (2009), 54.","journal-title":"Econometric Reviews"},{"key":"e_1_3_2_2_33_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need., Vol. 30 (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","unstructured":"Jun Xiao Hao Ye Xiangnan He Hanwang Zhang Fei Wu and Tat-Seng Chua. 2017. Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks. (2017) 3119--3125. https:\/\/doi.org\/10.24963\/ijcai.2017\/435","DOI":"10.24963\/ijcai.2017"},{"key":"e_1_3_2_2_36_1","volume-title":"Advances in Information Retrieval","author":"Zhang Weinan","unstructured":"Weinan Zhang, Tianming Du, and Jun Wang. 2016. Deep Learning over Multi-field Categorical Data. In Advances in Information Retrieval. Springer International Publishing, Cham, 45--57."}],"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\/3404835.3462936","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:20Z","timestamp":1750191500000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462936"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":36,"alternative-id":["10.1145\/3404835.3462936","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462936","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"}}]}}