{"id":"https://openalex.org/W7172016347","doi":"https://doi.org/10.1145/3828820.3828830","title":"Label-Balanced Graph Index for Filtered Approximate Nearest Neighbor Search with Low-Frequency Labels","display_name":"Label-Balanced Graph Index for Filtered Approximate Nearest Neighbor Search with Low-Frequency Labels","publication_year":2026,"publication_date":"2026-07-31","ids":{"openalex":"https://openalex.org/W7172016347","doi":"https://doi.org/10.1145/3828820.3828830"},"language":null,"primary_location":{"id":"doi:10.1145/3828820.3828830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3828820.3828830","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Scalable Scientific Data Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3828820.3828830","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144168608","display_name":"Hanchao Zheng","orcid":"https://orcid.org/0009-0006-9035-3740"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanchao Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-9035-3740","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144096740","display_name":"Yang Chen","orcid":"https://orcid.org/0009-0007-7516-2089"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-7516-2089","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5144158006","display_name":"Zhe Wu","orcid":"https://orcid.org/0009-0001-8233-8237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Wu","raw_affiliation_strings":["Independent Researcher, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-8233-8237","affiliations":[{"raw_affiliation_string":"Independent Researcher, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.7188000082969666},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.602400004863739},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5820000171661377},{"id":"https://openalex.org/keywords/nearest-neighbor-graph","display_name":"Nearest neighbor graph","score":0.5738000273704529},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5651000142097473},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5626000165939331},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4745999872684479},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4487000107765198}],"concepts":[{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.7188000082969666},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.602400004863739},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C90988772","wikidata":"https://www.wikidata.org/wiki/Q2855103","display_name":"Nearest neighbor graph","level":3,"score":0.5738000273704529},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5651000142097473},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5030999779701233},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C102164700","wikidata":"https://www.wikidata.org/wiki/Q17162702","display_name":"Nearest-neighbor chain algorithm","level":5,"score":0.4397999942302704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4392000138759613},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3840999901294708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3695000112056732},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C161986146","wikidata":"https://www.wikidata.org/wiki/Q4896845","display_name":"Best bin first","level":3,"score":0.35499998927116394},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32109999656677246},{"id":"https://openalex.org/C53661774","wikidata":"https://www.wikidata.org/wiki/Q13108095","display_name":"Cover tree","level":5,"score":0.3156999945640564},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3828820.3828830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3828820.3828830","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Scalable Scientific Data Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3828820.3828830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3828820.3828830","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th International Conference on Scalable Scientific Data Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1566135517","https://openalex.org/W1970319631","https://openalex.org/W2077815765","https://openalex.org/W2124509324","https://openalex.org/W2250539671","https://openalex.org/W2512971201","https://openalex.org/W2742272831","https://openalex.org/W2901613577","https://openalex.org/W2949985202","https://openalex.org/W2963213349","https://openalex.org/W2963469388","https://openalex.org/W2970641574","https://openalex.org/W2998702515","https://openalex.org/W3021397474","https://openalex.org/W3029865833","https://openalex.org/W3085011441","https://openalex.org/W3099700870","https://openalex.org/W3166125679","https://openalex.org/W3174809957","https://openalex.org/W4367046898","https://openalex.org/W4393183654","https://openalex.org/W4399174383","https://openalex.org/W4405623265","https://openalex.org/W4405623356"],"related_works":[],"abstract_inverted_index":{"Filtered":[0],"Approximate":[1],"Nearest":[2],"Neighbor":[3],"Search":[4],"(FANNS)":[5],"augments":[6],"vector":[7,18],"retrieval":[8],"with":[9,72,91,130],"categorical":[10],"label":[11,31],"predicates":[12],"and":[13,49,101,128,138],"is":[14,32],"now":[15],"standard":[16],"in":[17],"databases.":[19],"Existing":[20],"label-integrated":[21],"graph":[22],"indices,":[23],"however,":[24],"lose":[25],"substantial":[26],"recall":[27],"on":[28,75,80,125,133,151,157],"queries":[29],"whose":[30],"rare\u2014the":[33],"long-tail":[34],"regime":[35],"that":[36,68],"dominates":[37],"real":[38],"workloads.":[39,159],"We":[40],"trace":[41],"this":[42,81],"failure":[43],"to":[44,54,115,121,143],"construction:":[45],"distance-greedy":[46],"neighbor":[47],"selection":[48],"pruning":[50],"systematically":[51],"under-allocate":[52],"edges":[53],"low-frequency":[55],"labels,":[56],"leaving":[57],"their":[58,76,146],"subgraphs":[59],"poorly":[60],"connected.":[61],"Meanwhile,":[62],"high-frequency":[63],"labels":[64],"accumulate":[65],"redundant":[66],"edges\u2014slack":[67],"can":[69],"be":[70],"reallocated":[71],"limited":[73],"impact":[74],"search":[77],"quality.":[78],"Building":[79],"insight,":[82],"we":[83],"propose":[84],"LBGraph,":[85],"which":[86],"replaces":[87],"both":[88],"construction":[89],"phases":[90],"label-balanced":[92],"counterparts:":[93],"a":[94,102],"per-label":[95],"round-robin":[96],"candidate":[97],"pool":[98],"during":[99,105],"exploration,":[100],"label-then-distance":[103],"rule":[104],"pruning.":[106],"On":[107],"low-frequency-label":[108,152],"queries,":[109],"LBGraph":[110],"raises":[111],"recall@10":[112,150],"by":[113],"up":[114,142],"71":[116],"percentage":[117],"points":[118],"(from":[119],"20%":[120],"91%)":[122],"over":[123],"FilteredVamana":[124],"synthetic-label":[126],"SIFT1M":[127],"GIST,":[129],"smaller":[131],"gains":[132],"real-label":[134],"LAION1M.":[135],"Against":[136],"ACORN-\u03b3":[137],"StitchedVamana,":[139],"it":[140],"achieves":[141],"4":[144],"\u00d7":[145],"QPS":[147],"at":[148],"90%":[149],"workloads":[153],"while":[154],"staying":[155],"competitive":[156],"mixed":[158]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}