{"id":"https://openalex.org/W4413980314","doi":"https://doi.org/10.14778/3749646.3749660","title":"Extensible and Robust Evaluation of Similarity Queries","display_name":"Extensible and Robust Evaluation of Similarity Queries","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4413980314","doi":"https://doi.org/10.14778/3749646.3749660"},"language":"en","primary_location":{"id":"doi:10.14778/3749646.3749660","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3749646.3749660","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010481758","display_name":"Daniel Schmitt","orcid":"https://orcid.org/0009-0005-7656-7526"},"institutions":[{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Daniel Schmitt","raw_affiliation_strings":["University of Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"University of Salzburg, Austria","institution_ids":["https://openalex.org/I182212641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060455340","display_name":"Thomas H\u00fctter","orcid":"https://orcid.org/0000-0002-7190-6825"},"institutions":[{"id":"https://openalex.org/I4210126338","display_name":"Software Competence Center Hagenberg (Austria)","ror":"https://ror.org/02ks3nr96","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210126338"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Thomas H\u00fctter","raw_affiliation_strings":["Software Competence, Center Hagenberg, Austria"],"affiliations":[{"raw_affiliation_string":"Software Competence, Center Hagenberg, Austria","institution_ids":["https://openalex.org/I4210126338"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089328860","display_name":"Nikolaus Augsten","orcid":"https://orcid.org/0000-0002-3036-6201"},"institutions":[{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Nikolaus Augsten","raw_affiliation_strings":["University of Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"University of Salzburg, Austria","institution_ids":["https://openalex.org/I182212641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010481758"],"corresponding_institution_ids":["https://openalex.org/I182212641"],"apc_list":null,"apc_paid":null,"fwci":1.561,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86352787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"18","issue":"11","first_page":"3868","last_page":"3882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7524539232254028},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.6679231524467468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6107085347175598},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45860159397125244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31871724128723145},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10769400000572205},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.03070405125617981}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7524539232254028},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.6679231524467468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6107085347175598},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45860159397125244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31871724128723145},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10769400000572205},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.03070405125617981}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3749646.3749660","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3749646.3749660","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1495221665","https://openalex.org/W1527356121","https://openalex.org/W1588690145","https://openalex.org/W1625390266","https://openalex.org/W1875120328","https://openalex.org/W1969871814","https://openalex.org/W1973001156","https://openalex.org/W1993831977","https://openalex.org/W1998067572","https://openalex.org/W2016885468","https://openalex.org/W2019412213","https://openalex.org/W2022322548","https://openalex.org/W2033629528","https://openalex.org/W2037562342","https://openalex.org/W2052581258","https://openalex.org/W2065259291","https://openalex.org/W2073167797","https://openalex.org/W2087619740","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2100548092","https://openalex.org/W2105436061","https://openalex.org/W2107412086","https://openalex.org/W2119441285","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2121523964","https://openalex.org/W2136716899","https://openalex.org/W2150916025","https://openalex.org/W2156361796","https://openalex.org/W2157136665","https://openalex.org/W2162031302","https://openalex.org/W2162675341","https://openalex.org/W2163413133","https://openalex.org/W2164501930","https://openalex.org/W2166400748","https://openalex.org/W2167847032","https://openalex.org/W2205071250","https://openalex.org/W2209959171","https://openalex.org/W2257979135","https://openalex.org/W2269487093","https://openalex.org/W2294331997","https://openalex.org/W2295468252","https://openalex.org/W2396588571","https://openalex.org/W2574633002","https://openalex.org/W2585199909","https://openalex.org/W2752274179","https://openalex.org/W2763580087","https://openalex.org/W2793237766","https://openalex.org/W2795518213","https://openalex.org/W2798412430","https://openalex.org/W2903672378","https://openalex.org/W2942082747","https://openalex.org/W2949562252","https://openalex.org/W2954727071","https://openalex.org/W2964953836","https://openalex.org/W3006419569","https://openalex.org/W3007992747","https://openalex.org/W3102192406","https://openalex.org/W3103942683","https://openalex.org/W3136558723","https://openalex.org/W3154675738","https://openalex.org/W3176434378","https://openalex.org/W3203329898","https://openalex.org/W4233762723","https://openalex.org/W4244768633","https://openalex.org/W4281720128","https://openalex.org/W4285796263","https://openalex.org/W4312566537","https://openalex.org/W4385270123","https://openalex.org/W4386026606","https://openalex.org/W4386123435","https://openalex.org/W4413980314"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1948607442","https://openalex.org/W3004004161","https://openalex.org/W2044615423","https://openalex.org/W4247766898","https://openalex.org/W4244765761","https://openalex.org/W2361584951","https://openalex.org/W2364420803"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,165],"similarity":[3,11,67,86,109,184],"join":[4,12,68,87,185],"problem":[5],"from":[6,18,89],"a":[7,23,33,66,79,119,124,176],"systems":[8],"perspective.":[9],"A":[10,95],"retrieves":[13],"all":[14],"similar":[15],"record":[16],"pairs":[17],"two":[19,169],"collections":[20],"based":[21],"on":[22],"given":[24],"distance":[25,35,50,156],"function.":[26],"Existing":[27],"solutions":[28,41],"are":[29,42,111],"often":[30],"optimized":[31],"for":[32,71,108,181],"single":[34],"function":[36],"and":[37,52,73,118,147,155,178],"domain.":[38],"Such":[39],"monolithic":[40],"limited":[43],"in":[44],"both":[45],"their":[46,53],"extensibility":[47],"to":[48,100,122,143,164],"new":[49],"functions":[51,157],"robustness":[54],"against":[55],"changing":[56],"data":[57],"characteristics.":[58],"To":[59],"address":[60],"these":[61],"challenges,":[62],"we":[63],"introduce":[64],"Fast,":[65],"algorithm":[69],"designed":[70],"extensible":[72],"robust":[74],"query":[75,103,126],"evaluation.":[76],"It":[77,131],"leverages":[78],"novel":[80],"abstraction":[81],"called":[82],"reductions,":[83],"which":[84],"transform":[85],"problems":[88],"complex":[90],"domains":[91],"into":[92],"simpler":[93],"ones.":[94],"reduction":[96],"graph":[97],"is":[98],"constructed":[99],"systematically":[101],"enumerate":[102],"plans.":[104],"Since":[105],"cost":[106],"models":[107],"queries":[110],"typically":[112],"unavailable,":[113],"Fast":[114,160],"employs":[115],"runtime":[116],"partitioning":[117],"sampling-based":[120],"strategy":[121],"select":[123],"near-optimal":[125],"plan":[127],"with":[128],"performance":[129],"guarantees.":[130],"can":[132],"utilize":[133],"prebuilt":[134],"indexes":[135],"or":[136],"build":[137],"them":[138],"on-the-fly,":[139],"incorporating":[140],"caching":[141],"techniques":[142],"accelerate":[144],"index":[145],"construction":[146],"probing.":[148],"Extensive":[149],"experiments":[150],"across":[151],"diverse":[152],"datasets,":[153],"domains,":[154],"show":[158],"that":[159],"consistently":[161],"performs":[162],"close":[163],"optimal":[166],"plan.":[167],"Finally,":[168],"case":[170],"studies":[171],"highlight":[172],"its":[173,179],"strength":[174],"as":[175],"baseline":[177],"utility":[180],"prototyping":[182],"future":[183],"algorithms.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}