{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:12:45Z","timestamp":1785517965066,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,11]]},"DOI":"10.1145\/3828820.3828830","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T14:20:16Z","timestamp":1785507616000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Label-Balanced Graph Index for Filtered Approximate Nearest Neighbor Search with Low-Frequency Labels"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9035-3740","authenticated-orcid":false,"given":"Hanchao","family":"Zheng","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7516-2089","authenticated-orcid":false,"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8233-8237","authenticated-orcid":false,"given":"Zhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Independent Researcher, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Martin Aum\u00fcller Erik Bernhardsson and Alexander Faithfull. 2020. ANN-Benchmarks: A benchmarking tool for approximate nearest neighbor algorithms. Information Systems 87 (2020) 101374.","DOI":"10.1016\/j.is.2019.02.006"},{"key":"e_1_3_3_1_3_2","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. 2016. Efficient indexing of billion-scale datasets of deep descriptors. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2055\u20132063."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_13"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Yuzheng Cai Jiayang Shi Yizhuo Chen and Weiguo Zheng. 2024. Navigating labels and vectors: A unified approach to filtered approximate nearest neighbor search. Proceedings of the ACM on Management of Data 2 6 (2024) 1\u201327.","DOI":"10.1145\/3698822"},{"key":"e_1_3_3_1_6_2","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 neighborhood search. Advances in Neural Information Processing Systems 34 (2021) 5199\u20135212."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/177424.177609"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_3_1_9_2","unstructured":"Darren Edge Ha Trinh Newman Cheng Joshua Bradley Alex Chao Apurva Mody Steven Truitt Dasha Metropolitansky Robert\u00a0Osazuwa Ness and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.16130 (2024)."},{"key":"e_1_3_3_1_10_2","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:https:\/\/arXiv.org\/abs\/1707.00143 (2017)."},{"key":"e_1_3_3_1_11_2","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yixin Dai Jiawei Sun Haofen Wang Haofen Wang et\u00a0al. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.10997 2 1 (2023) 32."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","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\u2013755.","DOI":"10.1109\/TPAMI.2013.240"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583552"},{"key":"e_1_3_3_1_14_2","unstructured":"Rentong Guo Xiaofan Luan Long Xiang Xiao Yan Xiaomeng Yi Jigao Luo Qianya Cheng Weizhi Xu Jiarui Luo Frank Liu et\u00a0al. 2022. Manu: a cloud native vector database management system. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2206.13843 (2022)."},{"key":"e_1_3_3_1_15_2","first-page":"3887","volume-title":"International Conference on Machine Learning","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\u20133896."},{"key":"e_1_3_3_1_16_2","unstructured":"Gaurav Gupta Jonah Yi Benjamin Coleman Chen Luo Vihan Lakshman and Anshumali Shrivastava. 2023. Caps: A practical partition index for filtered similarity search. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.15014 (2023)."},{"key":"e_1_3_3_1_17_2","unstructured":"Masajiro Iwasaki and Daisuke Miyazaki. 2018. Optimization of indexing based on k-nearest neighbor graph for proximity search in high-dimensional data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.07355 (2018)."},{"key":"e_1_3_3_1_18_2","unstructured":"Suhas Jayaram\u00a0Subramanya Fnu Devvrit Harsha\u00a0Vardhan Simhadri Ravishankar Krishnawamy and Rohan Kadekodi. 2019. Diskann: Fast accurate billion-point nearest neighbor search on a single node. Advances in neural information processing Systems 32 (2019)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","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\u2013128.","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Jeff Johnson Matthijs Douze and Herv\u00e9 J\u00e9gou. 2019. Billion-scale similarity search with GPUs. IEEE transactions on big data 7 3 (2019) 535\u2013547.","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_3_1_23_2","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et\u00a0al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems 33 (2020) 9459\u20139474."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3284028.3284030"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467101"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Yu\u00a0A Malkov and Dmitry\u00a0A 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\u2013836.","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098108"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Aude Oliva and Antonio Torralba. 2001. Modeling the shape of the scene: A holistic representation of the spatial envelope. International journal of computer vision 42 3 (2001) 145\u2013175.","DOI":"10.1023\/A:1011139631724"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Liana Patel Peter Kraft Carlos Guestrin and Matei Zaharia. 2024. Acorn: Performant and predicate-agnostic search over vector embeddings and structured data. Proceedings of the ACM on Management of Data 2 3 (2024) 1\u201327.","DOI":"10.1145\/3654923"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_3_1_31_2","unstructured":"Pinecone. 2026. Filter by metadata | Pinecone Docs. https:\/\/docs.pinecone.io\/guides\/search\/filter-by-metadata. Accessed: 2026-05-10."},{"key":"e_1_3_3_1_32_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_3_1_34_2","unstructured":"Jie Ren Minjia Zhang and Dong Li. 2020. Hm-ann: Efficient billion-point nearest neighbor search on heterogeneous memory. Advances in Neural Information Processing Systems 33 (2020) 10672\u201310684."},{"key":"e_1_3_3_1_35_2","unstructured":"Facebook\u00a0AI Research. 2026. Faiss. https:\/\/github.com\/facebookresearch\/faiss. Accessed: 2026-05-10."},{"key":"e_1_3_3_1_36_2","unstructured":"Christoph Schuhmann Richard Vencu Romain Beaumont Robert Kaczmarczyk Clayton Mullis Aarush Katta Theo Coombes Jenia Jitsev and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2111.02114 (2021)."},{"key":"e_1_3_3_1_37_2","first-page":"177","volume-title":"NeurIPS 2021 Competitions and Demonstrations Track","author":"Simhadri Harsha\u00a0Vardhan","year":"2022","unstructured":"Harsha\u00a0Vardhan Simhadri, George Williams, Martin Aum\u00fcller, Matthijs Douze, Artem Babenko, Dmitry Baranchuk, Qi Chen, Lucas Hosseini, Ravishankar Krishnaswamny, Gopal Srinivasa, et\u00a0al. 2022. Results of the NeurIPS\u201921 challenge on billion-scale approximate nearest neighbor search. In NeurIPS 2021 Competitions and Demonstrations Track. PMLR, 177\u2013189."},{"key":"e_1_3_3_1_38_2","unstructured":"vespa. 2026. Attributes. https:\/\/docs.vespa.ai\/en\/content\/attributes.html. Accessed: 2026-05-10."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"e_1_3_3_1_40_2","unstructured":"Weaviate. 2026. Filtering | Weaviate Documentation. https:\/\/docs.weaviate.io\/weaviate\/concepts\/filtering. Accessed: 2026-05-10."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Chuangxian Wei Bin Wu Sheng Wang Renjie Lou Chaoqun Zhan Feifei Li and Yuanzhe Cai. 2020. AnalyticDB-V: A Hybrid Analytical Engine Towards Query Fusion for Structured and Unstructured Data. Proc. VLDB Endow. 13 12 (2020) 3152\u20133165.","DOI":"10.14778\/3415478.3415541"},{"key":"e_1_3_3_1_42_2","unstructured":"Lee Xiong Chenyan Xiong Ye Li Kwok-Fung Tang Jialin Liu Paul Bennett Junaid Ahmed and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2007.00808 (2020)."},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Yuexuan Xu Jianyang Gao Yutong Gou Cheng Long and Christian\u00a0S Jensen. 2024. irangegraph: Improvising range-dedicated graphs for range-filtering nearest neighbor search. Proceedings of the ACM on Management of Data 2 6 (2024) 1\u201326.","DOI":"10.1145\/3698814"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3386131"},{"key":"e_1_3_3_1_45_2","first-page":"377","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Zhang Qianxi","year":"2023","unstructured":"Qianxi Zhang, Shuotao Xu, Qi Chen, Guoxin Sui, Jiadong Xie, Zhizhen Cai, Yaoqi Chen, Yinxuan He, Yuqing Yang, Fan Yang, et\u00a0al. 2023. { VBASE} : Unifying online vector similarity search and relational queries via relaxed monotonicity. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 377\u2013395."},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Chaoji Zuo Miao Qiao Wenchao Zhou Feifei Li and Dong Deng. 2024. Serf: Segment graph for range-filtering approximate nearest neighbor search. Proceedings of the ACM on Management of Data 2 1 (2024) 1\u201326.","DOI":"10.1145\/3639324"}],"event":{"name":"SSDBM 2026: The International Conference on Scalable Scientific Data Management 2026","location":"San Diego , CA , USA","acronym":"SSDBM 2026"},"container-title":["Proceedings of the 38th International Conference on Scalable Scientific Data Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3828820.3828830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T16:30:35Z","timestamp":1785515435000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3828820.3828830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":45,"alternative-id":["10.1145\/3828820.3828830","10.1145\/3828820"],"URL":"https:\/\/doi.org\/10.1145\/3828820.3828830","relation":{},"subject":[],"published":{"date-parts":[[2026,8,11]]},"assertion":[{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}