{"id":"https://openalex.org/W7140204872","doi":"https://doi.org/10.48550/arxiv.2603.21710","title":"FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search","display_name":"FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7140204872","doi":"https://doi.org/10.48550/arxiv.2603.21710"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.21710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wu, Zekai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zekai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jin, Jiabao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Jiabao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng, Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhong, Xiaoyao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Xiaoyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tong, Yongxin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Yongxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shen, Zhitao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Zhitao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Song, Jingkuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Jingkuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shen, Heng Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Heng Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Lin, Xuemin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xuemin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.39800000190734863,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.39800000190734863,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.20020000636577606,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.18310000002384186,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7709000110626221},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6322000026702881},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.553600013256073},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5400999784469604},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5192000269889832},{"id":"https://openalex.org/keywords/nearest-neighbor-graph","display_name":"Nearest neighbor graph","score":0.37220001220703125},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.367000013589859},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.35850000381469727}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7709000110626221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347000241279602},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6322000026702881},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48910000920295715},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38429999351501465},{"id":"https://openalex.org/C90988772","wikidata":"https://www.wikidata.org/wiki/Q2855103","display_name":"Nearest neighbor graph","level":3,"score":0.37220001220703125},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.367000013589859},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3199000060558319},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C2778972660","wikidata":"https://www.wikidata.org/wiki/Q1666353","display_name":"Navigability","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C94475309","wikidata":"https://www.wikidata.org/wiki/Q6489154","display_name":"Large margin nearest neighbor","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C161986146","wikidata":"https://www.wikidata.org/wiki/Q4896845","display_name":"Best bin first","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C102164700","wikidata":"https://www.wikidata.org/wiki/Q17162702","display_name":"Nearest-neighbor chain algorithm","level":5,"score":0.26809999346733093},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.21710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21710","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"the":[1,38,153],"state-of-the-art":[2,154],"methods":[3,163,206],"for":[4,205],"high-dimensional":[5],"data":[6],"retrieval,":[7],"Approximate":[8],"Nearest":[9,101],"Neighbor":[10,102],"Search":[11],"(ANNS)":[12],"approaches":[13],"with":[14,91,152],"graph-based":[15,45,55,114,162,187],"indexes":[16,56,115],"have":[17],"attracted":[18],"increasing":[19],"attention":[20],"and":[21,34,75,127,131,142,158,168,199],"play":[22],"a":[23,58,84],"crucial":[24,64],"role":[25],"in":[26,65,72,78],"many":[27,66],"real-world":[28,67,175],"applications,":[29],"e.g.,":[30],"retrieval-augmented":[31],"generation":[32],"(RAG)":[33],"recommendation":[35],"systems.":[36],"Unlike":[37],"extensive":[39],"works":[40],"focused":[41],"on":[42,173],"designing":[43],"efficient":[44],"ANNS":[46,155,188],"methods,":[47,189],"this":[48],"paper":[49],"delves":[50],"into":[51,57],"merging":[52,169],"multiple":[53],"existing":[54,160],"single":[59],"one,":[60],"which":[61],"is":[62,182],"also":[63],"scenarios":[68],"(e.g.,":[69],"cluster":[70],"consolidation":[71],"distributed":[73],"systems":[74],"read-write":[76],"contention":[77],"real-time":[79],"vector":[80],"databases).":[81],"We":[82],"propose":[83],"Fast":[85],"Graph-based":[86],"Indexes":[87],"Merging":[88],"(FGIM)":[89],"framework":[90,151,181],"three":[92],"core":[93],"techniques:":[94],"(1)":[95],"Proximity":[96],"Graphs":[97],"(PGs)":[98],"to":[99,107,122,134,164,184,192],"$k$":[100],"Graph":[103],"($k$-NNG)":[104],"transformation":[105,136],"used":[106],"extract":[108],"potential":[109],"candidate":[110],"neighbors":[111,126],"from":[112],"input":[113],"through":[116],"cross-querying,":[117],"(2)":[118],"$k$-NNG":[119,133],"refinement":[120],"designed":[121],"identify":[123],"overlooked":[124],"high-quality":[125],"maintain":[128],"graph":[129,140],"connectivity,":[130],"(3)":[132],"PG":[135],"aimed":[137],"at":[138],"improving":[139],"navigability":[141],"enhancing":[143],"search":[144,215],"performance.":[145,216],"Then,":[146],"we":[147],"integrate":[148],"our":[149,179],"FGIM":[150,180],"method,":[156],"HNSW,":[157],"other":[159],"mainstream":[161,186],"demonstrate":[165],"its":[166],"generality":[167],"efficiency.":[170],"Extensive":[171],"experiments":[172],"six":[174],"datasets":[176],"show":[177],"that":[178],"applicable":[183],"various":[185],"achieves":[190],"up":[191],"3.5$\\times$":[193],"speedup":[194,204],"over":[195],"HNSW's":[196],"incremental":[197,208],"construction":[198],"an":[200],"average":[201],"of":[202],"7.9$\\times$":[203],"without":[207],"support,":[209],"while":[210],"maintaining":[211],"comparable":[212],"or":[213],"superior":[214]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-25T00:00:00"}