{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:27:39Z","timestamp":1764588459147,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,21]]},"DOI":"10.1145\/3583780.3615504","type":"proceedings-article","created":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T07:45:42Z","timestamp":1697874342000},"page":"4667-4673","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Unsupervised Multi-Modal Representation Learning for High Quality Retrieval of Similar Products at E-commerce Scale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5990-5168","authenticated-orcid":false,"given":"Kushal","family":"Kumar","sequence":"first","affiliation":[{"name":"Amazon, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8279-5811","authenticated-orcid":false,"given":"Tarik","family":"Arici","sequence":"additional","affiliation":[{"name":"Amazon, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0198-240X","authenticated-orcid":false,"given":"Tal","family":"Neiman","sequence":"additional","affiliation":[{"name":"Amazon, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7004-3570","authenticated-orcid":false,"given":"Jinyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Amazon, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1223-5912","authenticated-orcid":false,"given":"Shioulin","family":"Sam","sequence":"additional","affiliation":[{"name":"Amazon, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0604-8481","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Amazon, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5181-4712","authenticated-orcid":false,"given":"Hakan","family":"Ferhatosmanoglu","sequence":"additional","affiliation":[{"name":"Amazon, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8369-4825","authenticated-orcid":false,"given":"Ismail","family":"Tutar","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Block-scl: Blocking matters for supervised contrastive learning in product matching","author":"Almagro Mario","year":"2022","unstructured":"Mario Almagro , David Jim\u00e9nez , Diego Ortego , Emilio Almaz\u00e1n , and Eva Mart\u00ednez . Block-scl: Blocking matters for supervised contrastive learning in product matching , 2022 . Mario Almagro, David Jim\u00e9nez, Diego Ortego, Emilio Almaz\u00e1n, and Eva Mart\u00ednez. Block-scl: Blocking matters for supervised contrastive learning in product matching, 2022."},{"key":"e_1_3_2_1_2_1","volume-title":"Ann-benchmarks: A benchmarking tool for approximate nearest neighbor algorithms","author":"Aum\u00fcller Martin","year":"2018","unstructured":"Martin Aum\u00fcller , Erik Bernhardsson , and Alexander Faithfull . Ann-benchmarks: A benchmarking tool for approximate nearest neighbor algorithms , 2018 . Martin Aum\u00fcller, Erik Bernhardsson, and Alexander Faithfull. Ann-benchmarks: A benchmarking tool for approximate nearest neighbor algorithms, 2018."},{"key":"e_1_3_2_1_3_1","first-page":"2055","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Babenko Artem","year":"2016","unstructured":"Artem Babenko and Victor Lempitsky . Efficient indexing of billion-scale datasets of deep descriptors . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pages 2055 -- 2063 , 2016 . Artem Babenko and Victor Lempitsky. Efficient indexing of billion-scale datasets of deep descriptors. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2055--2063, 2016."},{"key":"e_1_3_2_1_4_1","volume-title":"Item2vec: Neural item embedding for collaborative filtering","author":"Barkan Oren","year":"2016","unstructured":"Oren Barkan and Noam Koenigstein . Item2vec: Neural item embedding for collaborative filtering , 2016 . Oren Barkan and Noam Koenigstein. Item2vec: Neural item embedding for collaborative filtering, 2016."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.ecnlp-1.25"},{"key":"e_1_3_2_1_6_1","volume-title":"A simple framework for contrastive learning of visual representations. CoRR, abs\/2002.05709","author":"Chen Ting","year":"2020","unstructured":"Ting Chen , Simon Kornblith , Mohammad Norouzi , and Geoffrey E. Hinton . A simple framework for contrastive learning of visual representations. CoRR, abs\/2002.05709 , 2020 . Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. A simple framework for contrastive learning of visual representations. CoRR, abs\/2002.05709, 2020."},{"key":"e_1_3_2_1_7_1","volume-title":"Unsupervised cross-lingual representation learning at scale","author":"Conneau Alexis","year":"2019","unstructured":"Alexis Conneau , Kartikay Khandelwal , Naman Goyal , Vishrav Chaudhary , Guillaume Wenzek , Francisco Guzm\u00e1n , Edouard Grave , Myle Ott , Luke Zettlemoyer , and Veselin Stoyanov . Unsupervised cross-lingual representation learning at scale , 2019 . Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzm\u00e1n, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. Unsupervised cross-lingual representation learning at scale, 2019."},{"key":"e_1_3_2_1_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . Bert: Pre-training of deep bidirectional transformers for language understanding , 2018 . Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding, 2018."},{"key":"e_1_3_2_1_9_1","volume-title":"M5product: Self-harmonized contrastive learning for e-commercial multi-modal pretraining","author":"Dong Xiao","year":"2021","unstructured":"Xiao Dong , Xunlin Zhan , Yangxin Wu , Yunchao Wei , Michael C. Kampffmeyer , Xiaoyong Wei , Minlong Lu , Yaowei Wang , and Xiaodan Liang . M5product: Self-harmonized contrastive learning for e-commercial multi-modal pretraining , 2021 . Xiao Dong, Xunlin Zhan, Yangxin Wu, Yunchao Wei, Michael C. Kampffmeyer, Xiaoyong Wei, Minlong Lu, Yaowei Wang, and Xiaodan Liang. M5product: Self-harmonized contrastive learning for e-commercial multi-modal pretraining, 2021."},{"key":"e_1_3_2_1_10_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale","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 , Jakob Uszkoreit , and Neil Houlsby . An image is worth 16x16 words: Transformers for image recognition at scale , 2020 . Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. An image is worth 16x16 words: Transformers for image recognition at scale, 2020."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01520"},{"key":"e_1_3_2_1_12_1","volume-title":"Angela Bitto- Nemling, and Sepp Hochreiter. Cloob: Modern hopfield networks with infoloob outperform clip","author":"F\u00fcrst Andreas","year":"2021","unstructured":"Andreas F\u00fcrst , Elisabeth Rumetshofer , Viet Tran , Hubert Ramsauer , Fei Tang , Johannes Lehner , David Kreil , Michael Kopp , G\u00fcnter Klambauer , Angela Bitto- Nemling, and Sepp Hochreiter. Cloob: Modern hopfield networks with infoloob outperform clip , 2021 . Andreas F\u00fcrst, Elisabeth Rumetshofer, Viet Tran, Hubert Ramsauer, Fei Tang, Johannes Lehner, David Kreil, Michael Kopp, G\u00fcnter Klambauer, Angela Bitto- Nemling, and Sepp Hochreiter. Cloob: Modern hopfield networks with infoloob outperform clip, 2021."},{"key":"e_1_3_2_1_13_1","volume-title":"E-commerce in your inbox: Product recommendations at scale. 06","author":"Grbovic Mihajlo","year":"2016","unstructured":"Mihajlo Grbovic , Vladan Radosavljevic , Nemanja Djuric , Narayan Bhamidipati , Jaikit Savla , Varun Bhagwan , and Doug Sharp . E-commerce in your inbox: Product recommendations at scale. 06 2016 . Mihajlo Grbovic, Vladan Radosavljevic, Nemanja Djuric, Narayan Bhamidipati, Jaikit Savla, Varun Bhagwan, and Doug Sharp. E-commerce in your inbox: Product recommendations at scale. 06 2016."},{"key":"e_1_3_2_1_14_1","volume-title":"Momentum contrast for unsupervised visual representation learning. CoRR, abs\/1911.05722","author":"He Kaiming","year":"2019","unstructured":"Kaiming He , Haoqi Fan , Yuxin Wu , Saining Xie , and Ross B. Girshick . Momentum contrast for unsupervised visual representation learning. CoRR, abs\/1911.05722 , 2019 . Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross B. Girshick. Momentum contrast for unsupervised visual representation learning. CoRR, abs\/1911.05722, 2019."},{"key":"e_1_3_2_1_15_1","volume-title":"Extending clip for category-to-image retrieval in e-commerce","author":"Hendriksen Mariya","year":"2021","unstructured":"Mariya Hendriksen , Maurits Bleeker , Svitlana Vakulenko , Nanne van Noord , Ernst Kuiper , and Maarten de Rijke . Extending clip for category-to-image retrieval in e-commerce , 2021 . Mariya Hendriksen, Maurits Bleeker, Svitlana Vakulenko, Nanne van Noord, Ernst Kuiper, and Maarten de Rijke. Extending clip for category-to-image retrieval in e-commerce, 2021."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01064"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_1_19_1","volume-title":"Approximate nearest neighbor search on high dimensional data - experiments, analyses, and improvement (v1.0)","author":"Li Wen","year":"2016","unstructured":"Wen Li , Ying Zhang , Yifang Sun , Wei Wang , Wenjie Zhang , and Xuemin Lin . Approximate nearest neighbor search on high dimensional data - experiments, analyses, and improvement (v1.0) , 2016 . Wen Li, Ying Zhang, Yifang Sun, Wei Wang, Wenjie Zhang, and Xuemin Lin. Approximate nearest neighbor search on high dimensional data - experiments, analyses, and improvement (v1.0), 2016."},{"key":"e_1_3_2_1_20_1","volume-title":"Decoupled weight decay regularization","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter . Decoupled weight decay regularization , 2017 . Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization, 2017."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Dinh The Luc. Pareto Optimality pages 481--515. Springer New York New York NY 2008.  Dinh The Luc. Pareto Optimality pages 481--515. Springer New York New York NY 2008.","DOI":"10.1007\/978-0-387-77247-9_18"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01752"},{"key":"e_1_3_2_1_23_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov Yu. A.","year":"2016","unstructured":"Yu. A. Malkov and D. A. Yashunin . Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs , 2016 . Yu. A. Malkov and D. A. Yashunin. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs, 2016."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524254"},{"key":"e_1_3_2_1_25_1","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research","author":"Radford Alec","year":"2021","unstructured":"Alec Radford , Jong Wook Kim , Chris Hallacy , Aditya Ramesh , Gabriel Goh , Sandhini Agarwal , Girish Sastry , Amanda Askell , Pamela Mishkin , Jack Clark , Gretchen Krueger , and Ilya Sutskever . Learning transferable visual models from natural language supervision. In Marina Meila and Tong Zhang, editors , Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research , pages 8748 -- 8763 . PMLR, 18--24 Jul 2021 . Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. Learning transferable visual models from natural language supervision. In Marina Meila and Tong Zhang, editors, Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 8748--8763. PMLR, 18--24 Jul 2021."},{"key":"e_1_3_2_1_26_1","unstructured":"Alec Radford Jong Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. Learning transferable visual models from natural language supervision. CoRR abs\/2103.00020 2021.  Alec Radford Jong Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. Learning transferable visual models from natural language supervision. CoRR abs\/2103.00020 2021."},{"key":"e_1_3_2_1_27_1","unstructured":"Amazon Web Services. Opensearch 2021.  Amazon Web Services. Opensearch 2021."},{"key":"e_1_3_2_1_28_1","volume-title":"Suhas Jayaram Subramanya, and Jingdong Wang. Results of the neurips'21 challenge on billion-scale approximate nearest neighbor search","author":"Simhadri Harsha Vardhan","year":"2022","unstructured":"Harsha Vardhan Simhadri , George Williams , Martin Aum\u00fcller , Matthijs Douze , Artem Babenko , Dmitry Baranchuk , Qi Chen , Lucas Hosseini , Ravishankar Krishnaswamy , Gopal Srinivasa , Suhas Jayaram Subramanya, and Jingdong Wang. Results of the neurips'21 challenge on billion-scale approximate nearest neighbor search , 2022 . Harsha Vardhan Simhadri, George Williams, Martin Aum\u00fcller, Matthijs Douze, Artem Babenko, Dmitry Baranchuk, Qi Chen, Lucas Hosseini, Ravishankar Krishnaswamy, Gopal Srinivasa, Suhas Jayaram Subramanya, and Jingdong Wang. Results of the neurips'21 challenge on billion-scale approximate nearest neighbor search, 2022."},{"key":"e_1_3_2_1_29_1","volume-title":"What makes for good views for contrastive learning?","author":"Tian Yonglong","year":"2020","unstructured":"Yonglong Tian , Chen Sun , Ben Poole , Dilip Krishnan , Cordelia Schmid , and Phillip Isola . What makes for good views for contrastive learning? , 2020 . Yonglong Tian, Chen Sun, Ben Poole, Dilip Krishnan, Cordelia Schmid, and Phillip Isola. What makes for good views for contrastive learning?, 2020."},{"key":"e_1_3_2_1_30_1","volume-title":"Representation learning with contrastive predictive coding. CoRR, abs\/1807.03748","author":"van den Oord A\u00e4ron","year":"2018","unstructured":"A\u00e4ron van den Oord , Yazhe Li , and Oriol Vinyals . Representation learning with contrastive predictive coding. CoRR, abs\/1807.03748 , 2018 . A\u00e4ron van den Oord, Yazhe Li, and Oriol Vinyals. Representation learning with contrastive predictive coding. CoRR, abs\/1807.03748, 2018."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219869"},{"key":"e_1_3_2_1_32_1","volume-title":"Unsupervised feature learning via non-parametric instance-level discrimination. CoRR, abs\/1805.01978","author":"Wu Zhirong","year":"2018","unstructured":"Zhirong Wu , Yuanjun Xiong , Stella X. Yu , and Dahua Lin . Unsupervised feature learning via non-parametric instance-level discrimination. CoRR, abs\/1805.01978 , 2018 . Zhirong Wu, Yuanjun Xiong, Stella X. Yu, and Dahua Lin. Unsupervised feature learning via non-parametric instance-level discrimination. CoRR, abs\/1805.01978, 2018."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"e_1_3_2_1_34_1","volume-title":"Decoupled contrastive learning","author":"Yeh Chun-Hsiao","year":"2021","unstructured":"Chun-Hsiao Yeh , Cheng-Yao Hong , Yen-Chi Hsu , Tyng-Luh Liu , Yubei Chen , and Yann LeCun . Decoupled contrastive learning , 2021 . Chun-Hsiao Yeh, Cheng-Yao Hong, Yen-Chi Hsu, Tyng-Luh Liu, Yubei Chen, and Yann LeCun. Decoupled contrastive learning, 2021."}],"event":{"name":"CIKM '23: The 32nd ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Birmingham United Kingdom","acronym":"CIKM '23"},"container-title":["Proceedings of the 32nd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615504","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583780.3615504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:55Z","timestamp":1750178215000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583780.3615504"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,21]]},"references-count":34,"alternative-id":["10.1145\/3583780.3615504","10.1145\/3583780"],"URL":"https:\/\/doi.org\/10.1145\/3583780.3615504","relation":{},"subject":[],"published":{"date-parts":[[2023,10,21]]},"assertion":[{"value":"2023-10-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}