{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T11:50:55Z","timestamp":1726314655825},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T00:00:00Z","timestamp":1714435200000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation Career","award":["CAREER-2048044"]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1838024"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2120333, 2112562, 1937435, 2140247"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-19-2-0107"],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583446","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:25Z","timestamp":1682551825000},"update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["NASRec: Weight Sharing Neural Architecture Search for Recommender Systems"],"prefix":"10.1145","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-9590-9433","authenticated-orcid":false,"given":"Tunhou","family":"Zhang","sequence":"first","affiliation":[{"name":"Duke University, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6177-9834","authenticated-orcid":false,"given":"Dehua","family":"Cheng","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-7447-6552","authenticated-orcid":false,"given":"Yuchen","family":"He","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5030-3005","authenticated-orcid":false,"given":"Zhengxing","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3098-2714","authenticated-orcid":false,"given":"Xiaoliang","family":"Dai","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-4224-5797","authenticated-orcid":false,"given":"Liang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9840-7754","authenticated-orcid":false,"given":"Feng","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Houston, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3228-6544","authenticated-orcid":false,"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"Duke University, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-1486-8412","authenticated-orcid":false,"given":"Yiran","family":"Chen","sequence":"additional","affiliation":[{"name":"Duke University, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-0027-4821","authenticated-orcid":false,"given":"Wei","family":"Wen","sequence":"additional","affiliation":[{"name":"Meta AI, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_4_1_1","volume-title":"Layer normalization. arXiv preprint arXiv:1607.06450","author":"Ba Jimmy\u00a0Lei","year":"2016","unstructured":"Jimmy\u00a0Lei Ba, Jamie\u00a0Ryan Kiros, and Geoffrey\u00a0E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_4_2_1","volume-title":"International Conference on Machine Learning. PMLR, 550\u2013559","author":"Bender Gabriel","year":"2018","unstructured":"Gabriel Bender, Pieter-Jan Kindermans, Barret Zoph, Vijay Vasudevan, and Quoc Le. 2018. Understanding and simplifying one-shot architecture search. In International Conference on Machine Learning. PMLR, 550\u2013559."},{"key":"e_1_3_2_4_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01433"},{"key":"e_1_3_2_4_4_1","volume-title":"Once-for-all: Train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791","author":"Cai Han","year":"2019","unstructured":"Han Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang, and Song Han. 2019. Once-for-all: Train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791 (2019)."},{"key":"e_1_3_2_4_5_1","volume-title":"Evaluating search engines by modeling the relationship between relevance and clicks. Advances in neural information processing systems 20","author":"Carterette Ben","year":"2007","unstructured":"Ben Carterette and Rosie Jones. 2007. Evaluating search engines by modeling the relationship between relevance and clicks. Advances in neural information processing systems 20 (2007)."},{"key":"e_1_3_2_4_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341261"},{"key":"e_1_3_2_4_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_4_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_4_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441727"},{"key":"e_1_3_2_4_10_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_4_11_1","volume-title":"Progressive Feature Interaction Search for Deep Sparse Network. Advances in Neural Information Processing Systems 34","author":"Gao Chen","year":"2021","unstructured":"Chen Gao, Yinfeng Li, Quanming Yao, Depeng Jin, and Yong Li. 2021. Progressive Feature Interaction Search for Deep Sparse Network. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_4_12_1","volume-title":"Modularized transfomer-based ranking framework. arXiv preprint arXiv:2004.13313","author":"Gao Luyu","year":"2020","unstructured":"Luyu Gao, Zhuyun Dai, and Jamie Callan. 2020. Modularized transfomer-based ranking framework. arXiv preprint arXiv:2004.13313 (2020)."},{"key":"e_1_3_2_4_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9153"},{"key":"e_1_3_2_4_14_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_4_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"e_1_3_2_4_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"e_1_3_2_4_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052605"},{"key":"e_1_3_2_4_18_1","volume-title":"Differentiable NAS Framework and Application to Ads CTR Prediction. arXiv preprint arXiv:2110.14812","author":"Krishna Ravi","year":"2021","unstructured":"Ravi Krishna, Aravind Kalaiah, Bichen Wu, Maxim Naumov, Dheevatsa Mudigere, Misha Smelyanskiy, and Kurt Keutzer. 2021. Differentiable NAS Framework and Application to Ads CTR Prediction. arXiv preprint arXiv:2110.14812 (2021)."},{"key":"e_1_3_2_4_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_4_20_1","volume-title":"Improved differentiable architecture search with early stopping. arXiv preprint arXiv:1909.06035","author":"Liang Hanwen","year":"2019","unstructured":"Hanwen Liang, Shifeng Zhang, Jiacheng Sun, Xingqiu He, Weiran Huang, Kechen Zhuang, and Zhenguo Li. 2019. Darts+: Improved differentiable architecture search with early stopping. arXiv preprint arXiv:1909.06035 (2019)."},{"key":"e_1_3_2_4_21_1","volume-title":"Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055","author":"Liu Hanxiao","year":"2018","unstructured":"Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)."},{"key":"e_1_3_2_4_22_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)."},{"key":"e_1_3_2_4_23_1","volume-title":"Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091","author":"Naumov Maxim","year":"2019","unstructured":"Maxim Naumov, Dheevatsa Mudigere, Hao-Jun\u00a0Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson\u00a0G Azzolini, 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 (2019)."},{"key":"e_1_3_2_4_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"e_1_3_2_4_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010002"},{"key":"e_1_3_2_4_26_1","unstructured":"Facebook Research. 2022. fvcore. https:\/\/github.com\/facebookresearch\/fvcore ."},{"key":"e_1_3_2_4_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242643"},{"key":"e_1_3_2_4_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939704"},{"key":"e_1_3_2_4_29_1","volume-title":"International Conference on Machine Learning. PMLR, 5877\u20135886","author":"So David","year":"2019","unstructured":"David So, Quoc Le, and Chen Liang. 2019. The evolved transformer. In International Conference on Machine Learning. PMLR, 5877\u20135886."},{"key":"e_1_3_2_4_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403137"},{"key":"e_1_3_2_4_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_2_4_32_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_4_33_1","volume-title":"Hat: Hardware-aware transformers for efficient natural language processing. arXiv preprint arXiv:2005.14187","author":"Wang Hanrui","year":"2020","unstructured":"Hanrui Wang, Zhanghao Wu, Zhijian Liu, Han Cai, Ligeng Zhu, Chuang Gan, and Song Han. 2020. Hat: Hardware-aware transformers for efficient natural language processing. arXiv preprint arXiv:2005.14187 (2020)."},{"key":"e_1_3_2_4_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_4_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"e_1_3_2_4_36_1","volume-title":"MaskNet: introducing feature-wise multiplication to CTR ranking models by instance-guided mask. arXiv preprint arXiv:2102.07619","author":"Wang Zhiqiang","year":"2021","unstructured":"Zhiqiang Wang, Qingyun She, and Junlin Zhang. 2021. MaskNet: introducing feature-wise multiplication to CTR ranking models by instance-guided mask. arXiv preprint arXiv:2102.07619 (2021)."},{"key":"e_1_3_2_4_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_39"},{"key":"e_1_3_2_4_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"e_1_3_2_4_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3543507.3583446","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583446","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T18:50:02Z","timestamp":1709232602000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":39,"alternative-id":["10.1145\/3543507.3583446","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583446","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}
