{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:29:00Z","timestamp":1778048940873,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"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":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539212","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"4493-4501","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Uni-Retriever: Towards Learning the Unified Embedding Based Retriever in Bing Sponsored Search"],"prefix":"10.1145","author":[{"given":"Jianjin","family":"Zhang","sequence":"first","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihao","family":"Han","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shitao","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruicheng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingxia","family":"Shao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Microsoft, Newark, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Premkumar","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Microsoft, Seattle, DC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Deng","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Xie","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_13"},{"key":"e_1_3_2_2_2_1","volume-title":"Pre-training tasks for embedding-based large-scale retrieval. arXiv preprint arXiv:2002.03932","author":"Chang Wei-Cheng","year":"2020","unstructured":"Wei-Cheng Chang, Felix X Yu, Yin-Wen Chang, Yiming Yang, and Sanjiv Kumar. 2020. Pre-training tasks for embedding-based large-scale retrieval. arXiv preprint arXiv:2002.03932 (2020)."},{"key":"e_1_3_2_2_3_1","volume-title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search. arXiv preprint arXiv:2111.08566","author":"Chen Qi","year":"2021","unstructured":"Qi Chen, Bing Zhao, Haidong Wang, Mingqin Li, Chuanjie Liu, Zengzhong Li, Mao Yang, and Jingdong Wang. 2021. SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search. arXiv preprint arXiv:2111.08566 (2021)."},{"key":"e_1_3_2_2_4_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_2_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330651"},{"key":"e_1_3_2_2_7_1","volume-title":"Fast approximate nearest neighbor search with the navigating spreading-out graph. arXiv preprint arXiv:1707.00143","author":"Fu Cong","year":"2017","unstructured":"Cong Fu, Chao Xiang, Changxu Wang, and Deng Cai. 2017. Fast approximate nearest neighbor search with the navigating spreading-out graph. arXiv preprint arXiv:1707.00143 (2017)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"e_1_3_2_2_9_1","volume-title":"Optimized product quantization","author":"Ge Tiezheng","year":"2013","unstructured":"Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. 2013. Optimized product quantization. IEEE transactions on pattern analysis and machine intelligence 36, 4 (2013), 744--755."},{"key":"e_1_3_2_2_10_1","volume-title":"Learning dense representations for entity retrieval. arXiv preprint arXiv:1909.10506","author":"Gillick Daniel","year":"2019","unstructured":"Daniel Gillick, Sayali Kulkarni, Larry Lansing, Alessandro Presta, Jason Baldridge, Eugene Ie, and Diego Garcia-Olano. 2019. Learning dense representations for entity retrieval. arXiv preprint arXiv:1909.10506 (2019)."},{"key":"e_1_3_2_2_11_1","volume-title":"International Conference on Machine Learning. PMLR, 3887--3896","author":"Guo Ruiqi","year":"2020","unstructured":"Ruiqi Guo, Philip Sun, Erik Lindgren, Quan Geng, David Simcha, Felix Chern, and Sanjiv Kumar. 2020. Accelerating large-scale inference with anisotropic vector quantization. In International Conference on Machine Learning. PMLR, 3887--3896."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_14_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_15_1","volume-title":"Embeddingbased retrieval in facebook search. In the 26th SIGKDD. 2553--2561","author":"Huang Jui-Ting","unstructured":"Jui-Ting Huang, Ashish Sharma, Shuying Sun, Li Xia, David Zhang, Philip Pronin, Janani Padmanabhan, Giuseppe Ottaviano, and Linjun Yang. 2020. Embeddingbased retrieval in facebook search. In the 26th SIGKDD. 2553--2561."},{"key":"e_1_3_2_2_16_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. NIPS 32 (2019)."},{"key":"e_1_3_2_2_17_1","volume-title":"Product quantization for nearest neighbor search","author":"Jegou Herve","year":"2010","unstructured":"Herve Jegou, Matthijs Douze, and Cordelia Schmid. 2010. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence 33, 1 (2010), 117--128."},{"key":"e_1_3_2_2_18_1","volume-title":"Searching in one billion vectors: re-rank with source coding","author":"J\u00e9gou Herv\u00e9","unstructured":"Herv\u00e9 J\u00e9gou, Romain Tavenard, Matthijs Douze, and Laurent Amsaleg. 2011. Searching in one billion vectors: re-rank with source coding. In ICASSP. IEEE."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Vladimir Karpukhin Barlas Oguz Sewon Min Patrick Lewis Ledell Wu Sergey Edunov Danqi Chen and Wen-tau Yih. 2020. Dense Passage Retrieval for Open- Domain Question Answering. In EMNLP. 6769--6781.","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1"},{"key":"e_1_3_2_2_22_1","volume-title":"AdsGNN: Behavior- Graph Augmented Relevance Modeling in Sponsored Search. arXiv preprint arXiv:2104.12080","author":"Li Chaozhuo","year":"2021","unstructured":"Chaozhuo Li, Bochen Pang, Yuming Liu, Hao Sun, Zheng Liu, Xing Xie, Tianqi Yang, Yanling Cui, Liangjie Zhang, and Qi Zhang. 2021. AdsGNN: Behavior- Graph Augmented Relevance Modeling in Sponsored Search. arXiv preprint arXiv:2104.12080 (2021)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313466"},{"key":"e_1_3_2_2_24_1","unstructured":"Yiding Liu Weixue Lu Suqi Cheng Daiting Shi Shuaiqiang Wang Zhicong Cheng and Dawei Yin. 2021. Pre-trained Language Model forWeb-scale Retrieval in Baidu Search. In SIGKDD. 3365--3375."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Yiqun Liu Kaushik Rangadurai Yunzhong He Siddarth Malreddy Xunlong Gui Xiaoyi Liu and Fedor Borisyuk. 2021. Que2search: Fast and accurate query and document understanding for search at facebook. In SIGKDD. 3376--3384.","DOI":"10.1145\/3447548.3467127"},{"key":"e_1_3_2_2_26_1","volume-title":"Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder. arXiv preprint arXiv:2102.09206","author":"Lu Shuqi","year":"2021","unstructured":"Shuqi Lu, Di He, Chenyan Xiong, Guolin Ke, Waleed Malik, Zhicheng Dou, Paul Bennett, Tieyan Liu, and Arnold Overwijk. 2021. Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder. arXiv preprint arXiv:2102.09206 (2021)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412747"},{"key":"e_1_3_2_2_28_1","volume-title":"dense, and attentional representations for text retrieval. arXiv preprint arXiv:2005.00181","author":"Luan Yi","year":"2020","unstructured":"Yi Luan, Jacob Eisenstein, Kristina Toutanova, and Michael Collins. 2020. Sparse, dense, and attentional representations for text retrieval. arXiv preprint arXiv:2005.00181 (2020)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_2_2_30_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov Yu A","year":"2018","unstructured":"Yu A Malkov and Dmitry A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence 42, 4 (2018), 824--836."},{"key":"e_1_3_2_2_31_1","volume-title":"Daxiang Dong, Hua Wu, and Haifeng Wang.","author":"Qu Yingqi","year":"2020","unstructured":"Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2020. RocketQA: An optimized training approach to dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2010.08191 (2020)."},{"key":"e_1_3_2_2_32_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2577348"},{"key":"e_1_3_2_2_34_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey et al. 2016. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_3_2_2_35_1","volume-title":"Training Microsoft News Recommenders with Pretrained Language Models in the Loop. arXiv e-prints","author":"Xiao Shitao","year":"2021","unstructured":"Shitao Xiao, Zheng Liu, Yingxia Shao, Tao Di, and Xing Xie. 2021. Training Microsoft News Recommenders with Pretrained Language Models in the Loop. arXiv e-prints (2021), arXiv--2102."},{"key":"e_1_3_2_2_36_1","volume-title":"Matching-oriented Product Quantization For Ad-hoc Retrieval. arXiv preprint arXiv:2104.07858","author":"Xiao Shitao","year":"2021","unstructured":"Shitao Xiao, Zheng Liu, Yingxia Shao, Defu Lian, and Xing Xie. 2021. Matching-oriented Product Quantization For Ad-hoc Retrieval. arXiv preprint arXiv:2104.07858 (2021)."},{"key":"e_1_3_2_2_37_1","unstructured":"Lee Xiong Chenyan Xiong Ye Li Kwok-Fung Tang Jialin Liu Paul N Bennett Junaid Ahmed and Arnold Overwijk. 2020. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In ICLR."},{"key":"e_1_3_2_2_38_1","unstructured":"Lee Xiong Chenyan Xiong Ye Li Kwok-Fung Tang Jialin Liu Paul N. Bennett Junaid Ahmed and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In ICLR."},{"key":"e_1_3_2_2_39_1","volume-title":"Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains. arXiv preprint arXiv:2106.13474","author":"Yao Yunzhi","year":"2021","unstructured":"Yunzhi Yao, Shaohan Huang,WenhuiWang, Li Dong, and FuruWei. 2021. Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains. arXiv preprint arXiv:2106.13474 (2021)."}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539212","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:59:58Z","timestamp":1750186798000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":39,"alternative-id":["10.1145\/3534678.3539212","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539212","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}