{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:06:22Z","timestamp":1779131182081,"version":"3.51.4"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"crossref","award":["2023YFB4502701"],"award-info":[{"award-number":["2023YFB4502701"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62232007"],"award-info":[{"award-number":["62232007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2026,5,18]]},"abstract":"<jats:p>Modern retrieval systems increasingly require integrating approximate nearest neighbor search (ANNS) with complex attribute filtering to handle hybrid queries in applications such as recommendation systems and retrieval-augmented generation (RAG). While HNSW-based inline-filtering methods show promise, existing approaches struggle to deliver high throughput under low-selectivity scenarios while balancing search efficiency, filtering generality, and index connectivity. To address these challenges, we propose FAVOR, an efficient filter-agnostic vector ANNS that supports arbitrary filtering conditions while maintaining stable performance across varying selectivity levels. FAVOR introduces three novel features: (1) an integrated architecture that unifies selectivity estimation and filtered ANNS execution, providing a cohesive solution for hybrid vector\u2013attribute queries; (2) a HNSW-based inline-filtering algorithm that introduces an exclusion distance mechanism to dynamically reshape the vector distance distribution, pushing non-target vectors away from the query while promoting valid candidates toward the query, thus improving search efficiency without compromising generality or graph connectivity; and (3) a selectivity-driven search selector that estimates query selectivity and dynamically routes queries between a pre-filtering brute-force algorithm for low-selectivity cases and an optimized HNSW-based search algorithm for other scenarios, ensuring consistent performance. Extensive experiments on real-world datasets demonstrate that FAVOR achieves a 1.3\u20135\u00d7 higher QPS at Recall@10 = 95% compared to state-of-the-art methods for arbitrary filtering conditions, while maintaining competitive performance even against tailored solutions in some filtering conditions.<\/jats:p>","DOI":"10.1145\/3802060","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:19:16Z","timestamp":1779128356000},"page":"1-25","source":"Crossref","is-referenced-by-count":0,"title":["FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3891-783X","authenticated-orcid":false,"given":"Junjie","family":"Song","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1964-9278","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, Hubei, China and National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9463-2045","authenticated-orcid":false,"given":"Guoyu","family":"Hu","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2924-6974","authenticated-orcid":false,"given":"Zhongle","family":"Xie","sequence":"additional","affiliation":[{"name":"Zhejiang University, Ningbo, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6925-6309","authenticated-orcid":false,"given":"Ming","family":"Yang","sequence":"additional","affiliation":[{"name":"Wuhan Technical University, Wuhan, Hubei, China and National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4446-1100","authenticated-orcid":false,"given":"Beng Chin","family":"Ooi","sequence":"additional","affiliation":[{"name":"Zhejiang University, Ningbo, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2161-8796","authenticated-orcid":false,"given":"Ke","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Le and Tom\u00e1s Mikolov","author":"Quoc","year":"2014","unstructured":"Quoc V. Le and Tom\u00e1s Mikolov. 2014. Distributed Representations of Sentences and Documents. In ICML, Vol. 32. JMLR.org, 1188-1196. http:\/\/proceedings.mlr.press\/v32\/le14.html"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375395.3387641"},{"key":"e_1_2_1_3_1","unstructured":"Patrick S. H. Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel Sebastian Riedel and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In NeurIPS. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6b493230205f780e1bc26945df7481e5-Abstract.html"},{"key":"e_1_2_1_4_1","first-page":"2206","article-title":"Improving Language Models by Retrieving from Trillions of Tokens","volume":"162","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 ICML, Vol. 162. 2206-2240. https:\/\/proceedings.mlr.press\/v162\/borgeaud22a.html","journal-title":"ICML"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476255"},{"key":"e_1_2_1_7_1","first-page":"824","volume-title":"TPAMI","volume":"42","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. TPAMI, Vol. 42, 4 (2018), 824-836."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698822"},{"key":"e_1_2_1_9_1","first-page":"4723","article-title":"SIEVE","volume":"18","author":"Li Zhaoheng","year":"2025","unstructured":"Zhaoheng Li, Silu Huang, Wei Ding, Yongjoo Park, and Jianjun Chen. 2025. SIEVE: Effective Filtered Vector Search with Collection of Indexes. PVLDB, Vol. 18, 11 (2025), 4723-4736.","journal-title":"Effective Filtered Vector Search with Collection of Indexes. PVLDB"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639324"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654923"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3746405.3746427"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327494"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2746539.2746553"},{"key":"e_1_2_1_15_1","first-page":"1225","article-title":"Practical and Optimal LSH for Angular Distance","author":"Andoni Alexandr","year":"2015","unstructured":"Alexandr Andoni, Piotr Indyk, Thijs Laarhoven, Ilya P. Razenshteyn, and Ludwig Schmidt. 2015. Practical and Optimal LSH for Angular Distance. In NeurIPS. 1225-1233. https:\/\/proceedings.neurips.cc\/paper\/2015\/hash\/2823f4797102ce1a1aec05359cc16dd9-Abstract.html","journal-title":"NeurIPS."},{"key":"e_1_2_1_16_1","volume-title":"Paired compressed cover trees guarantee a near linear parametrized complexity for all k-nearest neighbors search in an arbitrary metric space. CoRR","author":"Elkin Yury","year":"2022","unstructured":"Yury Elkin and Vitaliy Kurlin. 2022. Paired compressed cover trees guarantee a near linear parametrized complexity for all k-nearest neighbors search in an arbitrary metric space. CoRR, Vol. abs\/2201.06553 (2022). arXiv:2201.06553 https:\/\/arxiv.org\/abs\/2201.06553"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2343223"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397240"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321376"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.IS.2013.10.006"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557610"},{"key":"e_1_2_1_22_1","unstructured":"Mengzhao Wang Lingwei Lv Xiaoliang Xu Yuxiang Wang Qiang Yue and Jiongkang Ni. 2023. An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint. In NeurIPS. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/32e41d6b0a51a63a9a90697da19d235d-Abstract-Conference.html"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.15014"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583552"},{"key":"e_1_2_1_25_1","unstructured":"Joshua Engels Benjamin Landrum Shangdi Yu Laxman Dhulipala and Julian Shun. 2024. Approximate Nearest Neighbor Search with Window Filters. In ICML. OpenReview.net. https:\/\/openreview.net\/forum?id=8t8zBaGFar"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698814"},{"key":"e_1_2_1_27_1","first-page":"1118","article-title":"UNIFY","volume":"18","author":"Liang Anqi","year":"2024","unstructured":"Anqi Liang, Pengcheng Zhang, Bin Yao, Zhongpu Chen, Yitong Song, and Guangxu Cheng. 2024. UNIFY: Unified Index for Range Filtered Approximate Nearest Neighbors Search. PVLDB, Vol. 18, 4 (2024), 1118-1130. https:\/\/www.vldb.org\/pvldb\/vol18\/p1118-yao.pdf","journal-title":"PVLDB"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3603581.3603601"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2210.14958"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3749646.3749704"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.163414"},{"key":"e_1_2_1_32_1","volume-title":"An introduction to probability theory and its applications","author":"Feller William","unstructured":"William Feller. 1991. An introduction to probability theory and its applications, Volume 2. Vol. 2. John Wiley & Sons."},{"key":"e_1_2_1_33_1","volume-title":"Poisson Processes","author":"Kingman JFC","unstructured":"JFC Kingman. 1993. Poisson Processes. Oxford University Press, United Kingdom."},{"key":"e_1_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Jie Li Haifeng Liu Chuanghua Gui Jianyu Chen Zhenyun Ni and Ning Wang. 2019. The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform. arXiv:1908.07389 [cs.IR]","DOI":"10.1145\/3284028.3284030"},{"key":"e_1_2_1_35_1","volume-title":"Draper and Harry Smith","author":"Norman","year":"1998","unstructured":"Norman R. Draper and Harry Smith. 1998. Applied Regression Analysis."},{"key":"e_1_2_1_36_1","first-page":"63","article-title":"Dimensionality-Reduction Techniques for Approximate Nearest Neighbor Search: A Survey and Evaluation","volume":"48","author":"Wang Zeyu","year":"2024","unstructured":"Zeyu Wang, Haoran Xiong, Qitong Wang, Zhenying He, Peng Wang, Themis Palpanas, and Wei Wang. 2024. Dimensionality-Reduction Techniques for Approximate Nearest Neighbor Search: A Survey and Evaluation. IEEE Data Eng. Bull., Vol. 48, 3 (2024), 63-80. http:\/\/sites.computer.org\/debull\/A24sept\/p63.pdf","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725325"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588908"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00233"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725399"},{"key":"e_1_2_1_41_1","volume-title":"HENN: A Hierarchical Epsilon Net Navigation Graph for Approximate Nearest Neighbor Search. arXiv:2505.17368 [cs.DS] https:\/\/arxiv.org\/abs\/2505.17368","author":"Dehghankar Mohsen","year":"2025","unstructured":"Mohsen Dehghankar and Abolfazl Asudeh. 2025. HENN: A Hierarchical Epsilon Net Navigation Graph for Approximate Nearest Neighbor Search. arXiv:2505.17368 [cs.DS] https:\/\/arxiv.org\/abs\/2505.17368"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725413"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709730"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415541"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.14778\/3750601.3750700"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725401"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/3748191.3748193"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3802060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:21:41Z","timestamp":1779128501000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3802060"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,18]]}},"alternative-id":["10.1145\/3802060"],"URL":"https:\/\/doi.org\/10.1145\/3802060","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]}}}