{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:19:32Z","timestamp":1784179172304,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"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":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599897","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:13:58Z","timestamp":1691172838000},"page":"5520-5531","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Revisiting Neural Retrieval on Accelerators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7279-3318","authenticated-orcid":false,"given":"Jiaqi","family":"Zhai","sequence":"first","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1761-7530","authenticated-orcid":false,"given":"Zhaojie","family":"Gong","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3581-8910","authenticated-orcid":false,"given":"Yueming","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8385-7020","authenticated-orcid":false,"given":"Xiao","family":"Sun","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9754-9264","authenticated-orcid":false,"given":"Zheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1141-0870","authenticated-orcid":false,"given":"Fu","family":"Li","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0172-8698","authenticated-orcid":false,"given":"Xing","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_2_2_1","unstructured":"Felix Chern Blake Hechtman Andy Davis Ruiqi Guo David Majnemer and Sanjiv Kumar. 2022. TPU-KNN: K Nearest Neighbor Search at Peak FLOP\/s. In Advances in Neural Information Processing Systems.  Felix Chern Blake Hechtman Andy Davis Ruiqi Guo David Majnemer and Sanjiv Kumar. 2022. TPU-KNN: K Nearest Neighbor Search at Peak FLOP\/s. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3475943"},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding . In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics. 4171--4186 . Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics. 4171--4186."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186183"},{"key":"e_1_3_2_2_7_1","volume-title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning. Neural networks : the official journal of the International Neural Network Society","author":"Elfwing Stefan","year":"2017","unstructured":"Stefan Elfwing , Eiji Uchibe , and Kenji Doya . 2017. Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning. Neural networks : the official journal of the International Neural Network Society , Vol. 107 ( 2017 ), 3--11. Stefan Elfwing, Eiji Uchibe, and Kenji Doya. 2017. Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning. Neural networks : the official journal of the International Neural Network Society, Vol. 107 (2017), 3--11."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482362"},{"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","volume-title":"Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, AISTATS 2016","volume":"51","author":"Guo Ruiqi","year":"2016","unstructured":"Ruiqi Guo , Sanjiv Kumar , Krzysztof Choromanski , and David Simcha . 2016 . Quantization based Fast Inner Product Search . In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, AISTATS 2016 , Vol. 51 . 482--490. Ruiqi Guo, Sanjiv Kumar, Krzysztof Choromanski, and David Simcha. 2016. Quantization based Fast Inner Product Search. In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, AISTATS 2016, Vol. 51. 482--490."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan)","volume":"2","author":"Jordan M.I.","unstructured":"M.I. Jordan and R.A. Jacobs . 1993. Hierarchical mixtures of experts and the EM algorithm . In Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan) , Vol. 2 . 1339--1344 vol.2. M.I. Jordan and R.A. Jacobs. 1993. Hierarchical mixtures of experts and the EM algorithm. In Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan), Vol. 2. 1339--1344 vol.2."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357930"},{"key":"e_1_3_2_2_20_1","volume-title":"FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference. arXiv preprint arXiv:2101.05615","author":"Khudia Daya","year":"2021","unstructured":"Daya Khudia , Jianyu Huang , Protonu Basu , Summer Deng , Haixin Liu , Jongsoo Park , and Mikhail Smelyanskiy . 2021 . FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference. arXiv preprint arXiv:2101.05615 (2021). Daya Khudia, Jianyu Huang, Protonu Basu, Summer Deng, Haixin Liu, Jongsoo Park, and Mikhail Smelyanskiy. 2021. FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference. arXiv preprint arXiv:2101.05615 (2021)."},{"key":"e_1_3_2_2_21_1","volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR'15)","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015 . Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR'15) . Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations (ICLR'15)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2396761.2396831"},{"key":"e_1_3_2_2_23_1","volume-title":"Advances in Neural Information Processing Systems (NIPS'12","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E Hinton . 2012 . ImageNet Classification with Deep Convolutional Neural Networks . In Advances in Neural Information Processing Systems (NIPS'12 , Vol. 25). Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems (NIPS'12, Vol. 25)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2002.1019214"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357814"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357818"},{"key":"e_1_3_2_2_27_1","volume-title":"Mixed Precision Training. In International Conference on Learning Representations.","author":"Micikevicius Paulius","year":"2018","unstructured":"Paulius Micikevicius , Sharan Narang , Jonah Alben , Gregory Diamos , Erich Elsen , David Garcia , Boris Ginsburg , Michael Houston , Oleksii Kuchaiev , Ganesh Venkatesh , and Hao Wu . 2018 . Mixed Precision Training. In International Conference on Learning Representations. Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, and Hao Wu. 2018. Mixed Precision Training. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_28_1","unstructured":"Paulius Micikevicius Dusan Stosic Neil Burgess Marius Cornea Pradeep Dubey Richard Grisenthwaite Sangwon Ha Alexander Heinecke Patrick Judd John Kamalu etal 2022. FP8 formats for deep learning. arXiv preprint arXiv:2209.05433 (2022).  Paulius Micikevicius Dusan Stosic Neil Burgess Marius Cornea Pradeep Dubey Richard Grisenthwaite Sangwon Ha Alexander Heinecke Patrick Judd John Kamalu et al. 2022. FP8 formats for deep learning. arXiv preprint arXiv:2209.05433 (2022)."},{"key":"e_1_3_2_2_29_1","volume-title":"Product-Based Neural Networks for User Response Prediction. In 2016 IEEEE International Conference on Data Mining (ICDM). 1149--1154","author":"Qu Yanru","year":"2016","unstructured":"Yanru Qu , Han Cai , Kan Ren , Weinan Zhang , Yong Yu , Ying Wen , and Jun Wang . 2016 . Product-Based Neural Networks for User Response Prediction. In 2016 IEEEE International Conference on Data Mining (ICDM). 1149--1154 . Yanru Qu, Han Cai, Kan Ren, Weinan Zhang, Yong Yu, Ying Wen, and Jun Wang. 2016. Product-Based Neural Networks for User Response Prediction. In 2016 IEEEE International Conference on Data Mining (ICDM). 1149--1154."},{"key":"e_1_3_2_2_30_1","volume-title":"Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '12)","author":"Ram Parikshit","unstructured":"Parikshit Ram and Alexander G. Gray . 2012. Maximum Inner-Product Search Using Cone Trees . In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '12) . 931--939. Parikshit Ram and Alexander G. Gray. 2012. Maximum Inner-Product Search Using Cone Trees. In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '12). 931--939."},{"key":"e_1_3_2_2_31_1","volume-title":"Factorization Machines. In 2010 IEEE International Conference on Data Mining (ICDM). 995--1000","author":"Rendle Steffen","year":"2010","unstructured":"Steffen Rendle . 2010 . Factorization Machines. In 2010 IEEE International Conference on Data Mining (ICDM). 995--1000 . https:\/\/doi.org\/10.1109\/ICDM.2010.127 10.1109\/ICDM.2010.127 Steffen Rendle. 2010. Factorization Machines. In 2010 IEEE International Conference on Data Mining (ICDM). 995--1000. https:\/\/doi.org\/10.1109\/ICDM.2010.127"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412488"},{"key":"e_1_3_2_2_33_1","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Shrivastava Anshumali","year":"2014","unstructured":"Anshumali Shrivastava and Ping Li . 2014 . Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS) . In Advances in Neural Information Processing Systems , Vol. 27 . Anshumali Shrivastava and Ping Li. 2014. Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS). In Advances in Neural Information Processing Systems, Vol. 27."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_2_35_1","volume-title":"Xiaodong Cui, Wei Zhang, and Kailash Gopalakrishnan.","author":"Sun Xiao","year":"2019","unstructured":"Xiao Sun , Jungwook Choi , Chia-Yu Chen , Naigang Wang , Swagath Venkataramani , Vijayalakshmi Viji Srinivasan , Xiaodong Cui, Wei Zhang, and Kailash Gopalakrishnan. 2019 a. Hybrid 8-bit floating point (HFP8) training and inference for deep neural networks. Advances in neural information processing systems, Vol. 32 (2019). Xiao Sun, Jungwook Choi, Chia-Yu Chen, Naigang Wang, Swagath Venkataramani, Vijayalakshmi Viji Srinivasan, Xiaodong Cui, Wei Zhang, and Kailash Gopalakrishnan. 2019a. Hybrid 8-bit floating point (HFP8) training and inference for deep neural networks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441811"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS'16)","author":"Wang Hao","year":"2016","unstructured":"Hao Wang , Xingjian Shi , and Dit-Yan Yeung . 2016 . Collaborative Recurrent Autoencoder: Recommend While Learning to Fill in the Blanks . In Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS'16) . 415--423. Hao Wang, Xingjian Shi, and Dit-Yan Yeung. 2016. Collaborative Recurrent Autoencoder: Recommend While Learning to Fill in the Blanks. In Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS'16). 415--423."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219869"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463032"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172324"},{"key":"e_1_3_2_2_44_1","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20)","author":"Xin Xin","unstructured":"Xin Xin , Alexandros Karatzoglou , Ioannis Arapakis , and Joemon M. Jose . 2020. Self-Supervised Reinforcement Learning for Recommender Systems . In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20) . 931--940. Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, and Joemon M. Jose. 2020. Self-Supervised Reinforcement Learning for Recommender Systems. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20). 931--940."},{"key":"e_1_3_2_2_45_1","volume-title":"Mixed Negative Sampling for Learning Two-Tower Neural Networks in Recommendations. In Companion Proceedings of the Web Conference 2020 (WWW '20)","author":"Yang Ji","unstructured":"Ji Yang , Xinyang Yi , Derek Zhiyuan Cheng , Lichan Hong , Yang Li , Simon Xiaoming Wang , Taibai Xu , and Ed H. Chi . 2020 . Mixed Negative Sampling for Learning Two-Tower Neural Networks in Recommendations. In Companion Proceedings of the Web Conference 2020 (WWW '20) . 441--447. Ji Yang, Xinyang Yi, Derek Zhiyuan Cheng, Lichan Hong, Yang Li, Simon Xiaoming Wang, Taibai Xu, and Ed H. Chi. 2020. Mixed Negative Sampling for Learning Two-Tower Neural Networks in Recommendations. In Companion Proceedings of the Web Conference 2020 (WWW '20). 441--447."},{"key":"e_1_3_2_2_46_1","volume-title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model. In International Conference on Learning Representations (ICLR'18)","author":"Yang Zhilin","unstructured":"Zhilin Yang , Zihang Dai , Ruslan Salakhutdinov , and William W. Cohen . 2018 . Breaking the Softmax Bottleneck: A High-Rank RNN Language Model. In International Conference on Learning Representations (ICLR'18) . Zhilin Yang, Zihang Dai, Ruslan Salakhutdinov, and William W. Cohen. 2018. Breaking the Softmax Bottleneck: A High-Rank RNN Language Model. In International Conference on Learning Representations (ICLR'18)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989428"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467102"},{"key":"e_1_3_2_2_49_1","volume-title":"Deep Interest Network for Click-Through Rate Prediction (KDD '18)","author":"Zhou Guorui","year":"2018","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 (KDD '18) . 10 pages. 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 (KDD '18). 10 pages."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454644"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219826"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3526018"}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599897","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:41Z","timestamp":1750178261000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":52,"alternative-id":["10.1145\/3580305.3599897","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599897","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}