{"id":"https://openalex.org/W4404130155","doi":"https://doi.org/10.1145/3695830","title":"k-Clustering with Comparison and Distance Oracles","display_name":"k-Clustering with Comparison and Distance Oracles","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404130155","doi":"https://doi.org/10.1145/3695830"},"language":"en","primary_location":{"id":"doi:10.1145/3695830","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3695830","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","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/A5038532934","display_name":"Sainyam Galhotra","orcid":"https://orcid.org/0000-0003-2529-4036"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sainyam Galhotra","raw_affiliation_strings":["Department of Computer Science, Cornell University, Ithaca, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043765015","display_name":"Rahul Raychaudhury","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Raychaudhury","raw_affiliation_strings":["Department of Computer Science, Duke University, Durham, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015883931","display_name":"Stavros Sintos","orcid":"https://orcid.org/0000-0002-2114-8886"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stavros Sintos","raw_affiliation_strings":["Department of Computer Science, University of Illinois Chicago, Chicago, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Chicago, Chicago, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038532934"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22588072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":"5","first_page":"1","last_page":"26"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.6971031427383423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45232093334198},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3238299489021301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2942316234111786}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6971031427383423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45232093334198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3238299489021301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2942316234111786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695830","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3695830","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1971077223","https://openalex.org/W1973264045","https://openalex.org/W1974554406","https://openalex.org/W2008018349","https://openalex.org/W2042662336","https://openalex.org/W2045964207","https://openalex.org/W2058295780","https://openalex.org/W2066640191","https://openalex.org/W2068015060","https://openalex.org/W2092318232","https://openalex.org/W2095439633","https://openalex.org/W2128923212","https://openalex.org/W2131687179","https://openalex.org/W2153319198","https://openalex.org/W2183076570","https://openalex.org/W2283762717","https://openalex.org/W2342402489","https://openalex.org/W2559655401","https://openalex.org/W2580299352","https://openalex.org/W2596701210","https://openalex.org/W2612690371","https://openalex.org/W2614094703","https://openalex.org/W2657299459","https://openalex.org/W2747329762","https://openalex.org/W2754478492","https://openalex.org/W2798465726","https://openalex.org/W2798691796","https://openalex.org/W2799106927","https://openalex.org/W2803831948","https://openalex.org/W2808539549","https://openalex.org/W2899053911","https://openalex.org/W2912254316","https://openalex.org/W2946909130","https://openalex.org/W2950432447","https://openalex.org/W2963264680","https://openalex.org/W2963388857","https://openalex.org/W2963587548","https://openalex.org/W2963950688","https://openalex.org/W2993963457","https://openalex.org/W2999232157","https://openalex.org/W3004466950","https://openalex.org/W3012849342","https://openalex.org/W3104335155","https://openalex.org/W3131200319","https://openalex.org/W3176194034","https://openalex.org/W3186052405","https://openalex.org/W4212774754","https://openalex.org/W4238284510","https://openalex.org/W4240147959","https://openalex.org/W4245941037","https://openalex.org/W4281897885","https://openalex.org/W4387947464","https://openalex.org/W4390591024","https://openalex.org/W6622620221","https://openalex.org/W6643236230","https://openalex.org/W6715131512","https://openalex.org/W6737515860","https://openalex.org/W6740025986","https://openalex.org/W6744684649","https://openalex.org/W6748521397","https://openalex.org/W6758981106","https://openalex.org/W6766972467"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027"],"abstract_inverted_index":{"In":[0,75,125,143],"this":[1],"paper,":[2],"we":[3,22,192,224,267],"address":[4],"clustering":[5,188,251,275],"problems":[6],"in":[7,30,168,213],"scenarios":[8],"where":[9,33],"accurate":[10],"direct":[11],"access":[12],"to":[13,41,114,202,209,239,256,288,295],"the":[14,34,51,54,68,92,95,100,122,126,136,144,148,151,174,177,183,203,210,218,227,240,263,274,289,296],"full":[15],"dataset":[16,219],"is":[17,60,107,138,154,253],"impractical":[18],"or":[19,44,84,87],"impossible.":[20],"Instead,":[21],"leverage":[23],"oracle-based":[24],"methods,":[25],"which":[26],"are":[27],"particularly":[28],"valuable":[29],"real-world":[31],"applications":[32],"data":[35],"may":[36],"be":[37,80],"noisy,":[38],"restricted":[39],"due":[40],"privacy":[42],"concerns":[43],"sheer":[45],"volume.":[46],"We":[47,116,160,243],"utilize":[48],"two":[49,71,103,118,131],"oracles,":[50],"quadruplet":[52,58,123,175,204,264,290],"and":[53,110,176,186,206,249,292],"distance":[55,96,101,153,178,211,241,297],"oracle.":[56,124,179,242,265,298],"The":[57],"oracle":[59,63,97,113,205,212,291],"a":[61,108,157,162,169,235],"weaker":[62],"that":[64,172,197,246],"only":[65,262],"approximately":[66],"compares":[67],"distances":[69],"of":[70,73,102,165,182,230,281],"pairs":[72,132],"vertices.":[74],"practice,":[76],"these":[77],"oracles":[78],"can":[79],"implemented":[81],"using":[82,261],"crowdsourcing":[83],"training":[85],"classifiers":[86],"other":[88,93],"predictive":[89],"models.":[90,216],"On":[91],"hand,":[94],"returns":[98],"exactly":[99],"vertices,":[104,283],"so":[105],"it":[106],"stronger":[109],"more":[111],"expensive":[112],"implement.":[115],"consider":[117,161],"noise":[119,128,146,215],"models":[120],"for":[121,247,272],"adversarial":[127],"model,":[129,147],"if":[130],"have":[133],"similar":[134],"distances,":[135],"response":[137],"chosen":[139],"by":[140,233,278],"an":[141],"adversary.":[142],"probabilistic":[145],"pair":[149],"with":[150,156],"smaller":[152],"returned":[155],"constant":[158,194,269],"probability.":[159],"set":[163,280],"V":[164],"n":[166],"vertices":[167],"metric":[170],"space":[171],"supports":[173],"For":[180],"each":[181],"k-center,":[184],"k-median,":[185],"k-means":[187,250],"problem":[189],"on":[190],"V,":[191],"design":[193],"approximation":[195,228,260,270],"algorithms":[196,232,271],"perform":[198],"roughly":[199,285],"O(nk)":[200,286],"calls":[201,208,238,287,294],"O(k^2)":[207,293],"both":[214],"When":[217],"has":[220],"low":[221],"intrinsic":[222],"dimension,":[223],"significantly":[225],"improve":[226],"factors":[229],"our":[231],"performing":[234,284],"few":[236],"additional":[237],"also":[244],"show":[245],"k-median":[248],"there":[252],"no":[254],"hope":[255],"return":[257],"any":[258,279],"sublinear":[259],"Finally,":[266],"give":[268],"estimating":[273],"cost":[276],"induced":[277],"k":[282]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}