{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:14:10Z","timestamp":1779174850115,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"National Science Foundation of China","award":["NSFC No. 62422206"],"award-info":[{"award-number":["NSFC No. 62422206"]}]},{"name":"Hong Kong Research Grants Council","award":["GRF 152043\/23E"],"award-info":[{"award-number":["GRF 152043\/23E"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730004","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:25:28Z","timestamp":1752456328000},"page":"2524-2533","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["IGP: Efficient Multi-Vector Retrieval via Proximity Graph Index"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5396-6998","authenticated-orcid":false,"given":"Zheng","family":"Bian","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, ShenZhen, China and Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9619-4924","authenticated-orcid":false,"given":"Man Lung","family":"Yiu","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8424-0092","authenticated-orcid":false,"given":"Bo","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2017. Quora Reference. https:\/\/quoradata.quora.com\/First-Quora-Dataset-Release-Question-Pairs"},{"key":"e_1_3_2_1_2_1","unstructured":"2022. Lotte Data Source. https:\/\/github.com\/stanford-futuredata\/ColBERT\/blob\/main\/LoTTE.md"},{"key":"e_1_3_2_1_3_1","unstructured":"2022. MS MARCO Quora and HotpotQA Data Source. https:\/\/huggingface.co\/datasets\/BeIR\/beir"},{"key":"e_1_3_2_1_4_1","volume-title":"Mark Hildebrand, Mariano Tepper, and Theodore L. Willke.","author":"Aguerrebere Cecilia","year":"2023","unstructured":"Cecilia Aguerrebere, Ishwar Singh Bhati, Mark Hildebrand, Mariano Tepper, and Theodore L. Willke. 2023. Similarity search in the blink of an eye with compressed indices. PVLDB (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Moses Charikar. 2002. Similarity estimation techniques from rounding algorithms. In STOC.","DOI":"10.1145\/509961.509965"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Nick Craswell Bhaskar Mitra Emine Yilmaz Daniel Campos Ellen M. Voorhees and Ian Soboroff. 2021. TREC Deep Learning Track: Reusable Test Collections in the Large Data Regime. In SIGIR.","DOI":"10.1145\/3404835.3463249"},{"key":"e_1_3_2_1_7_1","volume-title":"Mirrokni","author":"Datar Mayur","year":"2004","unstructured":"Mayur Datar, Nicole Immorlica, Piotr Indyk, and Vahab S. Mirrokni. 2004. Locality-sensitive hashing scheme based on p-stable distributions. In SoCG."},{"key":"e_1_3_2_1_8_1","volume-title":"DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries. In NeurIPS.","author":"Engels Joshua","year":"2023","unstructured":"Joshua Engels, Benjamin Coleman, Vihan Lakshman, and Anshumali Shrivastava. 2023. DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries. In NeurIPS."},{"key":"e_1_3_2_1_9_1","volume-title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. In SIGIR.","author":"Formal Thibault","year":"2021","unstructured":"Thibault Formal, Benjamin Piwowarski, and St\u00e9phane Clinchant. 2021. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. In SIGIR."},{"key":"e_1_3_2_1_10_1","volume-title":"Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph. PVLDB","author":"Fu Cong","year":"2019","unstructured":"Cong Fu, Chao Xiang, Changxu Wang, and Deng Cai. 2019. Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph. PVLDB (2019)."},{"key":"e_1_3_2_1_11_1","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 ICML."},{"key":"e_1_3_2_1_12_1","volume-title":"Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring. In ICLR.","author":"Humeau Samuel","year":"2020","unstructured":"Samuel Humeau, Kurt Shuster, Marie-Anne Lachaux, and Jason Weston. 2020. Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring. In ICLR."},{"key":"e_1_3_2_1_13_1","volume-title":"MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding. In NeurIPS.","author":"Jayaram Rajesh","year":"2024","unstructured":"Rajesh Jayaram, Laxman Dhulipala, Majid Hadian, Jason Lee, and Vahab Mirrokni. 2024. MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding. In NeurIPS."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_1_15_1","volume-title":"Relevance-guided Supervision for OpenQA with ColBERT. Trans. Assoc. Comput. Linguistics","author":"Khattab Omar","year":"2021","unstructured":"Omar Khattab, Christopher Potts, and Matei Zaharia. 2021. Relevance-guided Supervision for OpenQA with ColBERT. Trans. Assoc. Comput. Linguistics (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Omar Khattab and Matei Zaharia. 2020. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT. In SIGIR.","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Carlos Lassance and St\u00e9phane Clinchant. 2022. An Efficiency Study for SPLADE Models. In SIGIR.","DOI":"10.1145\/3477495.3531833"},{"key":"e_1_3_2_1_18_1","volume-title":"Eugene Yang, James Mayfield, and Douglas W. Oard.","author":"Lawrie Dawn J.","year":"2024","unstructured":"Dawn J. Lawrie, Efsun Selin Kayi, Eugene Yang, James Mayfield, and Douglas W. Oard. 2024. PLAID SHIRTTT for Large-Scale Streaming Dense Retrieval. In SIGIR."},{"key":"e_1_3_2_1_19_1","volume-title":"Overview of the TREC 2023 NeuCLIR Track. In TREC.","author":"Lawrie Dawn J.","year":"2023","unstructured":"Dawn J. Lawrie, Sean MacAvaney, James Mayfield, Paul McNamee, Douglas W. Oard, Luca Soldaini, and Eugene Yang. 2023. Overview of the TREC 2023 NeuCLIR Track. In TREC."},{"key":"e_1_3_2_1_20_1","volume-title":"Tao Lei, Iftekhar Naim, Ming-Wei Chang, and Vincent Zhao.","author":"Lee Jinhyuk","year":"2023","unstructured":"Jinhyuk Lee, Zhuyun Dai, Sai Meher Karthik Duddu, Tao Lei, Iftekhar Naim, Ming-Wei Chang, and Vincent Zhao. 2023. Rethinking the Role of Token Retrieval in Multi-Vector Retrieval. In NeurIPS."},{"key":"e_1_3_2_1_21_1","volume-title":"CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval. In ACL.","author":"Li Minghan","year":"2023","unstructured":"Minghan Li, Sheng-Chieh Lin, Barlas Oguz, Asish Ghoshal, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, and Xilun Chen. 2023. CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval. In ACL."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2909204"},{"key":"e_1_3_2_1_23_1","volume-title":"Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations. In SIGIR.","author":"Lin Jimmy","year":"2021","unstructured":"Jimmy Lin, Xueguang Ma, Sheng-Chieh Lin, Jheng-Hong Yang, Ronak Pradeep, and Rodrigo Nogueira. 2021. Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations. In SIGIR."},{"key":"e_1_3_2_1_24_1","unstructured":"Weizhe Lin Jinghong Chen Jingbiao Mei Alexandru Coca and Bill Byrne. 2023. Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering. In NeurIPS."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Jie Liu Xiao Yan Xinyan Dai Zhirong Li James Cheng and Ming-Chang Yang. 2020. Understanding and Improving Proximity Graph Based Maximum Inner Product Search. In AAAI.","DOI":"10.1609\/aaai.v34i01.5344"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Wanqi Liu Hanchen Wang Ying Zhang Wei Wang Lu Qin and Xuemin Lin. 2021. EI-LSH: An early-termination driven I\/O efficient incremental c-approximate nearest neighbor search. VLDB J. (2021).","DOI":"10.1007\/s00778-020-00635-4"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Yi Luan Jacob Eisenstein Kristina Toutanova and Michael Collins. 2021. Sparse Dense and Attentional Representations for Text Retrieval. Trans. Assoc. Comput. Linguistics (2021).","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Sean MacAvaney and Nicola Tonellotto. 2024. A Reproducibility Study of PLAID. In SIGIR.","DOI":"10.1145\/3626772.3657856"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331317"},{"key":"e_1_3_2_1_30_1","volume-title":"Yashunin","author":"Malkov Yury A.","year":"2020","unstructured":"Yury A. Malkov and Dmitry A. Yashunin. 2020. Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs. IEEE Trans. Pattern Anal. Mach. Intell. (2020)."},{"key":"e_1_3_2_1_31_1","unstructured":"Stanislav Morozov and Artem Babenko. 2018. Non-metric Similarity Graphs for Maximum Inner Product Search. In NeurIPS."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Franco Maria Nardini Cosimo Rulli and Rossano Venturini. 2024. Efficient Multi-vector Dense Retrieval with Bit Vectors. In ECIR.","DOI":"10.1007\/978-3-031-56060-6_1"},{"key":"e_1_3_2_1_33_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016. Ms marco: A human-generated machine reading comprehension dataset. (2016)."},{"key":"e_1_3_2_1_34_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In CoCo@NeurIPS.","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In CoCo@NeurIPS."},{"key":"e_1_3_2_1_35_1","volume-title":"Passage Re-ranking with BERT. CoRR abs\/1901.04085","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira and Kyunghyun Cho. 2019. Passage Re-ranking with BERT. CoRR abs\/1901.04085 (2019)."},{"key":"e_1_3_2_1_36_1","unstructured":"James Jie Pan Jianguo Wang and Guoliang Li. 2024. Survey of vector database management systems. VLDB J. (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"SCV: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors. In COLING.","author":"Park Cheoneum","year":"2025","unstructured":"Cheoneum Park, Seohyeong Jeong, Minsang Kim, KyungTae Lim, and Yong-Hun Lee. 2025. SCV: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors. In COLING."},{"key":"e_1_3_2_1_38_1","volume-title":"Daxiang Dong, Hua Wu, and Haifeng Wang.","author":"Qu Yingqi","year":"2021","unstructured":"Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2021. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering. In NAACL-HLT."},{"key":"e_1_3_2_1_39_1","volume-title":"Text REtrieval Conference.","author":"Robertson Stephen E.","year":"1994","unstructured":"Stephen E. Robertson, Steve Walker, Susan Jones, Micheline Hancock-Beaulieu, and Mike Gatford. 1994. Okapi at TREC-3. In Text REtrieval Conference."},{"key":"e_1_3_2_1_40_1","unstructured":"Devendra Singh Sachan Mike Lewis Mandar Joshi Armen Aghajanyan Wen-tau Yih Joelle Pineau and Luke Zettlemoyer. 2022. Improving Passage Retrieval with Zero-Shot Question Generation. In EMNLP."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557325"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Keshav Santhanam Omar Khattab Jon Saad-Falcon Christopher Potts and Matei Zaharia. 2022. ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction. In NAACL-HLT.","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_43_1","unstructured":"Shiguang Wu Wenda Wei Mengqi Zhang Zhumin Chen Jun Ma Zhaochun Ren Maarten de Rijke and Pengjie Ren. 2024. Generative Retrieval as Multi-Vector Dense Retrieval. In SIGIR."},{"key":"e_1_3_2_1_44_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_1_45_1","volume-title":"Manning","author":"Yang Zhilin","year":"2018","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. In EMNLP."},{"key":"e_1_3_2_1_46_1","volume-title":"FILIP: Fine-grained Interactive Language-Image Pre-Training. In ICLR.","author":"Yao Lewei","year":"2022","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2022. FILIP: Fine-grained Interactive Language-Image Pre-Training. In ICLR."},{"key":"e_1_3_2_1_47_1","volume-title":"Jensen","author":"Zhao Xi","year":"2023","unstructured":"Xi Zhao, Bolong Zheng, Xiaomeng Yi, Xiaofan Luan, Charles Xie, Xiaofang Zhou, and Christian S. Jensen. 2023. FARGO: Fast Maximum Inner Product Search via Global Multi-Probing. PVLDB (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393377"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:19:26Z","timestamp":1755865166000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730004"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":48,"alternative-id":["10.1145\/3726302.3730004","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730004","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}