{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:19:17Z","timestamp":1784179157139,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,22]]},"DOI":"10.1145\/3696410.3714822","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T22:52:18Z","timestamp":1745362338000},"page":"1626-1637","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Retrieval with Learned Similarities"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4138-6379","authenticated-orcid":false,"given":"Bailu","family":"Ding","sequence":"first","affiliation":[{"name":"Microsoft Research, Redmond, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7279-3318","authenticated-orcid":false,"given":"Jiaqi","family":"Zhai","sequence":"additional","affiliation":[{"name":"Meta, Bellevue, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. ANN Benchmarks. https:\/\/ann-benchmarks.com\/. Accessed: 2024-08-06."},{"key":"e_1_3_2_1_2_1","unstructured":"Emmanuel Bengio Pierre-Luc Bacon Joelle Pineau and Doina Precup. 2016. Conditional Computation in Neural Networks for faster models. arXiv:1511.06297 [cs.LG] https:\/\/arxiv.org\/abs\/1511.06297"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/361002.361007"},{"key":"e_1_3_2_1_4_1","volume-title":"Oh (Eds.)","volume":"35","author":"Bevilacqua Michele","year":"2022","unstructured":"Michele Bevilacqua, Giuseppe Ottaviano, Patrick Lewis, Scott Yih, Sebastian Riedel, and Fabio Petroni. 2022. Autoregressive Search Engines: Generating Substrings as Document Identifiers. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 31668--31683. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/ cd88d62a2063fdaf7ce6f9068fb15dcd-Paper-Conference.pdf"},{"key":"e_1_3_2_1_5_1","first-page":"17","article-title":"Improving Language Models by Retrieving from Trillions of Tokens. In International Conference on Machine Learning","volume":"2022","author":"Borgeaud Sebastian","year":"2022","unstructured":"Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, Diego de Las Casas, Aurelia Guy, Jacob Menick, Roman Ring, Tom Hennigan, Saffron Huang, Loren Maggiore, Chris Jones, Albin Cassirer, Andy Brock, Michela Paganini, Geoffrey Irving, Oriol Vinyals, Simon Osindero, Karen Simonyan, Jack W. Rae, Erich Elsen, and Laurent Sifre. 2022. Improving Language Models by Retrieving from Trillions of Tokens. In International Conference on Machine Learning, ICML 2022, 17--23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 2206--2240. https:\/\/proceedings.mlr.press\/v162\/borgeaud22a.html","journal-title":"ICML"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680091"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01138"},{"key":"e_1_3_2_1_9_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."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_11_1","volume-title":"Autoregressive Entity Retrieval. In 9th International Conference on Learning Representations, ICLR 2021","author":"Cao Nicola De","year":"2021","unstructured":"Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2021. Autoregressive Entity Retrieval. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=5k8F6UU39V"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186183"},{"key":"e_1_3_2_1_14_1","volume-title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning. CoRR abs\/1702.03118","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. CoRR abs\/1702.03118 (2017). arXiv:1702.03118 http:\/\/arxiv.org\/abs\/1702.03118"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482362"},{"key":"e_1_3_2_1_16_1","unstructured":"Daniel Gillick Alessandro Presta and Gaurav Singh Tomar. 2018. End-to-End Retrieval in Continuous Space. arXiv:1811.08008 [cs.IR]"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/645925.671516"},{"key":"e_1_3_2_1_18_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."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525302"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_1_22_1","volume-title":"4th International Conference on Learning Representations, ICLR","author":"Hidasi Bal\u00e1zs","year":"2016","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2016. Session-based Recommendations with Recurrent Neural Networks. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2--4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1511.06939"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of The 33rd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1444","author":"Jasinska Kalina","year":"2016","unstructured":"Kalina Jasinska, Krzysztof Dembczynski, Robert Busa-Fekete, Karlson Pfannschmidt, Timo Klerx, and Eyke Hullermeier. 2016. Extreme F-measure Maximization using Sparse Probability Estimates. In Proceedings of The 33rd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 48), Maria Florina Balcan and Kilian Q. Weinberger (Eds.). PMLR, New York, New York, USA, 1435--1444. https:\/\/proceedings.mlr.press\/v48\/jasinska16.html"},{"key":"e_1_3_2_1_24_1","volume-title":"Ravishankar Krishnawamy, and Rohan Kadekodi.","author":"Subramanya Suhas Jayaram","year":"2019","unstructured":"Suhas Jayaram Subramanya, Fnu Devvrit, Harsha Vardhan Simhadri, Ravishankar Krishnawamy, and Rohan Kadekodi. 2019. DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node. In Advances in Neural Information Processing Systems, H.Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. https:\/\/proceedings.neurips. cc\/paper_files\/paper\/2019\/file\/09853c7fb1d3f8ee67a61b6bf4a7f8e6-Paper.pdf"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496517"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2002.1019214"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357814"},{"key":"e_1_3_2_1_36_1","volume-title":"DecoupledWeight Decay Regularization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. DecoupledWeight Decay Regularization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_1_39_1","volume-title":"Garnett (Eds.)","volume":"31","author":"Morozov Stanislav","year":"2018","unstructured":"Stanislav Morozov and Artem Babenko. 2018. Non-metric Similarity Graphs for Maximum Inner Product Search. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/ paper_files\/paper\/2018\/file\/229754d7799160502a143a72f6789927-Paper.pdf"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_42_1","unstructured":"Rodrigo Nogueira and Jimmy Lin. 2019. From doc2query to doctttttquery. https:\/\/cs.uwaterloo.ca\/~jimmylin\/publications\/Nogueira_Lin_2019_ docTTTTTquery-v2.pdf"},{"key":"e_1_3_2_1_43_1","volume-title":"CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs.","author":"Ootomo Hiroyuki","year":"2024","unstructured":"Hiroyuki Ootomo, Akira Naruse, Corey Nolet, RayWang, Tamas Feher, and Yong Wang. 2024. CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs."},{"key":"e_1_3_2_1_44_1","volume-title":"Liu","author":"Raffel Colin","year":"2023","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2023. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv:1910.10683 [cs.LG] https:\/\/arxiv.org\/abs\/1910.10683"},{"key":"e_1_3_2_1_45_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."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412488"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_49_1","volume-title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=B1ckMDqlg","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, *Azalia Mirhoseini, *Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"e_1_3_2_1_50_1","unstructured":"Yikang Shen Zheyu Zhang Tianyou Cao Shawn Tan Zhenfang Chen and Chuang Gan. 2023. ModuleFormer: Modularity Emerges from Mixture-of-Experts. arXiv:2306.04640 [cs.CL] https:\/\/arxiv.org\/abs\/2306.04640"},{"key":"e_1_3_2_1_51_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."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_2_1_53_1","volume-title":"Levine (Eds.)","volume":"36","author":"Sun Weiwei","year":"2023","unstructured":"Weiwei Sun, Lingyong Yan, Zheng Chen, Shuaiqiang Wang, Haichao Zhu, Pengjie Ren, Zhumin Chen, Dawei Yin, Maarten Rijke, and Zhaochun Ren. 2023. Learning to Tokenize for Generative Retrieval. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 46345--46361. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/ 91228b942a4528cdae031c1b68b127e8-Paper-Conference.pdf"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371830"},{"key":"e_1_3_2_1_55_1","unstructured":"Yi Tay Vinh Q. Tran Mostafa Dehghani Jianmo Ni Dara Bahri Harsh Mehta Zhen Qin Kai Hui Zhe Zhao Jai Gupta Tal Schuster William W. Cohen and Donald Metzler. 2022. Transformer Memory as a Differentiable Search Index. In Advances in Neural Information Processing Systems Alice H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=Vu-B0clPfq"},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of the First Learning on Graphs Conference (Proceedings of Machine Learning Research","volume":"17","author":"Wang Yiwei","year":"2022","unstructured":"Yiwei Wang, Bryan Hooi, Yozen Liu, Tong Zhao, Zhichun Guo, and Neil Shah. 2022. Flashlight: Scalable Link Prediction With Effective Decoders. In Proceedings of the First Learning on Graphs Conference (Proceedings of Machine Learning Research, Vol. 198), Bastian Rieck and Razvan Pascanu (Eds.). PMLR, 14:1--14:17. https:\/\/proceedings.mlr.press\/v198\/wang22a.html"},{"key":"e_1_3_2_1_57_1","volume-title":"Oh (Eds.)","volume":"35","author":"Wang Yujing","year":"2022","unstructured":"Yujing Wang, Yingyan Hou, Haonan Wang, Ziming Miao, Shibin Wu, Qi Chen, Yuqing Xia, Chengmin Chi, Guoshuai Zhao, Zheng Liu, Xing Xie, Hao Sun, Weiwei Deng, Qi Zhang, and Mao Yang. 2022. A Neural Corpus Indexer for Document Retrieval. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 25600--25614. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/a46156bd3579c3b268108ea6aca71d13-Paper-Conference.pdf"},{"key":"e_1_3_2_1_58_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)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599897"},{"key":"e_1_3_2_1_60_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"58509","author":"Zhai Jiaqi","year":"2024","unstructured":"Jiaqi Zhai, Lucy Liao, Xing Liu, Yueming Wang, Rui Li, Xuan Cao, Leon Gao, Zhaojie Gong, Fangda Gu, Jiayuan He, Yinghai Lu, and Yu Shi. 2024. Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 58484--58509. https:\/\/proceedings.mlr.press\/v235\/zhai24a.html"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989428"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219826"},{"key":"e_1_3_2_1_63_1","unstructured":"Shengyao Zhuang Houxing Ren Linjun Shou Jian Pei Ming Gong Guido Zuccon and Daxin Jiang. 2023. Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation. arXiv:2206.10128 [cs.IR] https:\/\/arxiv.org\/abs\/2206.10128"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3526018"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714822","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:42Z","timestamp":1750295922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714822"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":64,"alternative-id":["10.1145\/3696410.3714822","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714822","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}