[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83534-en":3,"doc-seo-83534-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83534,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Approximate Nearest Neighbor Search with Graph Range Filters","Vector databases underpin high-dimensional retrieval in AI systems by supporting approximate nearest neighbor (ANN) search. Filtered ANN methods retrieve vectors satisfying attribute constraints, yet common filter types typically cover only simple numeric ranges or categorical existence checks, limiting use in structured, real-world settings. This paper studies filtered ANN with graph range filters, requiring returned vectors to lie within a specified distance from the query node in a filter graph. The proposed DLH uses distance-aware labeling sets with hashing compression and Bloom-filter compression, and DLH-M adds query-node memoization for higher efficiency. Experiments show up to 70.3% throughput gains with recall above 98.5%.","Approximate Nearest Neighbor Search with Graph Range Filters  \nQian Tao  \nBeihang University Beijing, China [qiantao@buaa.edu.cn](qiantao@buaa.edu.cn)  \nYuntao Jiang  \nBeihang University Beijing, China [yuntaojiang@buaa.edu.cn](yuntaojiang@buaa.edu.cn)  \nYongxin Tong∗ Beihang University Beijing, China [yxtong@buaa.edu.cn](yxtong@buaa.edu.cn)  \nYu Sun  \nNankai University Tianjin, China [sunyu@nankai.edu.cn](sunyu@nankai.edu.cn)  \narXiv :2607 .00727v 1 [ cs .DB] 1 Jul 2026  \nABSTRACT  \nVector databases have become a fundamental component for highdimensional vector retrieval in artificial intelligence applications. Recent research has focused on filtered approximate nearest neighbor search (filtered ANN), which involves retrieving the nearest vectors that satisfy a given attribute-based filter. However, existing filters are generally limited to numerical range constraints or categorical existence checks, which restricts their applicability in more complex, real-world scenarios. In this paper, we investigate filtered ANN using graph range filters, where the retrieved vectors must be within a specified distance from the query node in a predefined filter graph. To address this problem, we propose DLH, a Distance-aware Labeling index with Hashing compression. DLH creates distance-aware labeling sets to enable efficient graph range filters via the simplified set intersection operations. Large labeling sets are further compressed into Bloom filters to improve query efficiency in DLH. Furthermore, recognizing that the query node is always involved in in-range queries of the graph range filters, we enhance DLH by memoizing the intermediate hashing index for the query node, yielding an optimized version called DLH-M. Experimental evaluations on diverse datasets demonstrate that DLH and DLH-M improve throughput by up to 70.3%, and could maintain recall rates over 98. 5% with limited extra storage, validating the practical availability of the proposed solution.  \nArtifact Availability:  \nThe source code has been made available at [https://github.com/TaoLbr1993/](https://github.com/TaoLbr1993/)[ ](https://github.com/TaoLbr1993/)DLH.  \n1 INTRODUCTION  \nAs a fundamental component of modern artificial intelligence, vector databases have attracted considerable attention due to their powerful vector search capabilities, and have become a core component of Retrieval Augmented Generation (RAG) systems [11, 15] . They underpin a wide range of Intelligent tasks, including domain knowledge question answering [37], text generation [39], image generation [50], etc. The core functionality of vector databases lies in approximate nearest neighbor (ANN) search, which retrieves the semantically nearest vectors to a given query vector.  \nIn practical applications, vector data is frequently coupled with diverse attributes, necessitating filtered ANN search to retrieve the nearest vectors that strictly adhere to specific attribute-based filters. For instance, a product search on an e-commercial platform may require identifying similar items that were sold within the past three weeks. While current filtering criteria effectively handle numerical ranges [26, 48, 51] and categorical existence checks [3, 17, 30], they are typically defined on oversimplified or low-cardinality attributes.  \n∗ Yongxin Tong is the corresponding author.  \nFigure 1: ANN search with graph range filters.  \nThis limitation constrains their applicability in complex, real-world filtered ANN search scenarios.  \nReal-world applications require filtered ANN search over complicated structured attributes. In scenarios such as graph-based RAG [9, 29], agent memory management [7], and anti-money laundering [21], similarity is evaluated among vectors that are constrained by a pre-defined filter graph. This motivates a novel yet practical filtered ANN search setting. In this setting, the attributes associated with vectors are derived from graph-structured data, rather than independent labels. To illu","cbCaiv7FZYXR2Hov","https://ap.wps.com/l/cbCaiv7FZYXR2Hov","pdf",3561144,4,1,13,"English","en",105,"# Introduction\n## Motivation and Problem Setting\n## Challenges of ANNGR","[{\"question\":\"What is the new filtered ANN setting proposed in the paper?\",\"answer\":\"The paper studies approximate nearest neighbor search with graph range filters, where retrieved vectors must be similar to the query and also located within a specified hop-distance neighborhood of the query node in a filter graph.\"},{\"question\":\"Why do existing filtered ANN filters have limited applicability?\",\"answer\":\"Existing filters mainly support numeric range constraints or categorical existence checks, which are often defined on oversimplified or low-cardinality attributes and do not capture more complex structured attributes found in real applications.\"},{\"question\":\"How does DLH improve efficiency for graph range filters?\",\"answer\":\"DLH builds distance-aware labeling sets so graph range filters can be answered through simplified set intersections, then compresses large labeling sets with Bloom filters to speed up queries. It further introduces DLH-M by memoizing intermediate hashing results for the query node to optimize repeated in-range computation.\"}]",1784188667,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"approximate-nearest-neighbor-search-with-graph-range-filters","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/approximate-nearest-neighbor-search-with-graph-range-filters/83534/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the new filtered ANN setting proposed in the paper?","Question",{"text":75,"@type":76},"The paper studies approximate nearest neighbor search with graph range filters, where retrieved vectors must be similar to the query and also located within a specified hop-distance neighborhood of the query node in a filter graph.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why do existing filtered ANN filters have limited applicability?",{"text":80,"@type":76},"Existing filters mainly support numeric range constraints or categorical existence checks, which are often defined on oversimplified or low-cardinality attributes and do not capture more complex structured attributes found in real applications.",{"name":82,"@type":73,"acceptedAnswer":83},"How does DLH improve efficiency for graph range filters?",{"text":84,"@type":76},"DLH builds distance-aware labeling sets so graph range filters can be answered through simplified set intersections, then compresses large labeling sets with Bloom filters to speed up queries. It further introduces DLH-M by memoizing intermediate hashing results for the query node to optimize repeated in-range computation.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]