{"id":"https://openalex.org/W4206699712","doi":"https://doi.org/10.1007/s10618-021-00811-2","title":"Provable randomized rounding for minimum-similarity diversification","display_name":"Provable randomized rounding for minimum-similarity diversification","publication_year":2022,"publication_date":"2022-01-04","ids":{"openalex":"https://openalex.org/W4206699712","doi":"https://doi.org/10.1007/s10618-021-00811-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/35401029"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-021-00811-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-021-00811-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-021-00811-2.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-021-00811-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046836740","display_name":"Bruno Ordozgoiti","orcid":"https://orcid.org/0000-0001-6938-3159"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Bruno Ordozgoiti","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075832299","display_name":"Ananth Mahadevan","orcid":"https://orcid.org/0000-0001-5401-5716"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ananth Mahadevan","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086657710","display_name":"Antonis Matakos","orcid":"https://orcid.org/0000-0002-1003-7101"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Antonis Matakos","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022164041","display_name":"Aristides Gionis","orcid":"https://orcid.org/0000-0002-5211-112X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Aristides Gionis","raw_affiliation_strings":["Division of Theoretical Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Theoretical Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046836740"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00726568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"2","first_page":"709","last_page":"738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9980000257492065,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.995199978351593,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/rounding","display_name":"Rounding","score":0.7011154890060425},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5895063877105713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.554823100566864},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5295665860176086},{"id":"https://openalex.org/keywords/randomized-rounding","display_name":"Randomized rounding","score":0.460616797208786},{"id":"https://openalex.org/keywords/submodular-set-function","display_name":"Submodular set function","score":0.45065850019454956},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42195698618888855},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38798922300338745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36950838565826416},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.34043335914611816},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2815350294113159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23548710346221924}],"concepts":[{"id":"https://openalex.org/C136625980","wikidata":"https://www.wikidata.org/wiki/Q663208","display_name":"Rounding","level":2,"score":0.7011154890060425},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5895063877105713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.554823100566864},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5295665860176086},{"id":"https://openalex.org/C32029473","wikidata":"https://www.wikidata.org/wiki/Q7292010","display_name":"Randomized rounding","level":3,"score":0.460616797208786},{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.45065850019454956},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42195698618888855},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38798922300338745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36950838565826416},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.34043335914611816},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2815350294113159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23548710346221924},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s10618-021-00811-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-021-00811-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-021-00811-2.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},{"id":"pmid:35401029","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35401029","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data mining and knowledge discovery","raw_type":null},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/112556","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/814f8454-42e5-4f35-8f5d-ae609b6dc226","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},{"id":"pmh:oai:helda.helsinki.fi:10138/342329","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/342329","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8964643","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8964643","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Min Knowl Discov","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s10618-021-00811-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-021-00811-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-021-00811-2.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G265104915","display_name":null,"funder_award_id":"EC H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4109205870","display_name":null,"funder_award_id":"317085","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G7066629376","display_name":null,"funder_award_id":"325117","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G899169222","display_name":null,"funder_award_id":"871042","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320321394","display_name":"Aalto-Yliopisto","ror":"https://ror.org/020hwjq30"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4206699712.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W10962629","https://openalex.org/W169553655","https://openalex.org/W1526762477","https://openalex.org/W1526974953","https://openalex.org/W1591442626","https://openalex.org/W1680189815","https://openalex.org/W1891203375","https://openalex.org/W1968518318","https://openalex.org/W1973296628","https://openalex.org/W1973343848","https://openalex.org/W1975917757","https://openalex.org/W1984818365","https://openalex.org/W1999942773","https://openalex.org/W2001554016","https://openalex.org/W2004759812","https://openalex.org/W2007815473","https://openalex.org/W2014793162","https://openalex.org/W2022191808","https://openalex.org/W2032352143","https://openalex.org/W2038428842","https://openalex.org/W2054501360","https://openalex.org/W2071563913","https://openalex.org/W2090739911","https://openalex.org/W2097951507","https://openalex.org/W2100419635","https://openalex.org/W2104266030","https://openalex.org/W2104456647","https://openalex.org/W2107126505","https://openalex.org/W2129866531","https://openalex.org/W2132314908","https://openalex.org/W2141429664","https://openalex.org/W2144407406","https://openalex.org/W2144416612","https://openalex.org/W2152228468","https://openalex.org/W2155912844","https://openalex.org/W2160321559","https://openalex.org/W2167066679","https://openalex.org/W2430322353","https://openalex.org/W2555561851","https://openalex.org/W2735816714","https://openalex.org/W2790891482","https://openalex.org/W2798663050","https://openalex.org/W2950038749","https://openalex.org/W3098711454","https://openalex.org/W3138773240","https://openalex.org/W4205585032","https://openalex.org/W4250589301"],"related_works":["https://openalex.org/W1581948717","https://openalex.org/W2268207117","https://openalex.org/W4300488607","https://openalex.org/W2951095575","https://openalex.org/W2105543801","https://openalex.org/W4313357160","https://openalex.org/W1530375092","https://openalex.org/W1916943706","https://openalex.org/W2062310236","https://openalex.org/W2543175834"],"abstract_inverted_index":{"When":[0],"searching":[1],"for":[2,62,212,227],"information":[3],"in":[4,14,20,34,82,93,168,269],"a":[5,22,45,72,105,116,125,143,153,209,243],"data":[6],"collection,":[7],"we":[8,85,99,151,181],"are":[9,32,266],"often":[10],"interested":[11],"not":[12],"only":[13],"finding":[15,44,104],"relevant":[16],"items,":[17,109],"but":[18],"also":[19],"assembling":[21],"diverse":[23,106],"set,":[24],"so":[25],"as":[26],"to":[27,88,160,187,200,235],"explore":[28],"different":[29],"concepts":[30],"that":[31,66,183,241,258,265],"present":[33,167],"the":[35,76,94,101,121,133,139,164,213,262,270],"data.":[36],"This":[37],"problem":[38,102],"has":[39,224],"been":[40],"researched":[41],"extensively.":[42],"However,":[43],"set":[46,107],"of":[47,79,103,108,132,135,138,163,215,220],"items":[48,141],"with":[49],"minimal":[50],"pairwise":[51,136],"similarities":[52,137],"can":[53,175],"be":[54,89,176],"computationally":[55],"challenging,":[56],"and":[57,142,202,223,256],"most":[58],"existing":[59],"works":[60],"striving":[61],"quality":[63],"guarantees":[64],"assume":[65],"item":[67,111],"relatedness":[68,112],"is":[69,113,158,185,197,219],"measured":[70,114],"by":[71,115],"distance":[73],"function.":[74,118],"Given":[75],"widespread":[77],"use":[78],"similarity":[80,117],"functions":[81],"many":[83],"domains,":[84],"believe":[86],"this":[87,97,173,233],"an":[90,193,237],"important":[91],"gap":[92],"literature.":[95,271],"In":[96],"paper":[98],"study":[100],"when":[110],"We":[119,231,248],"formulate":[120],"diversification":[122],"task":[123],"using":[124,178,192,252],"flexible,":[126],"broadly":[127],"applicable":[128],"minimization":[129],"objective,":[130],"consisting":[131],"sum":[134],"selected":[140],"relevance":[144],"penalty":[145],"term.":[146],"To":[147],"find":[148],"good":[149,190],"solutions":[150,191],"adopt":[152],"randomized":[154,239],"rounding":[155],"strategy,":[156],"which":[157,196,218],"challenging":[159],"analyze":[161],"because":[162],"cardinality":[165],"constraint":[166],"our":[169,250],"formulation.":[170],"Even":[171],"though":[172],"obstacle":[174],"overcome":[177],"dependent":[179],"rounding,":[180],"show":[182,257],"it":[184,259],"possible":[186],"obtain":[188],"provably":[189],"independent":[194,221],"approach,":[195],"faster,":[198],"simpler":[199],"implement":[201],"completely":[203],"parallelizable.":[204],"Our":[205],"analysis":[206],"relies":[207],"on":[208],"novel":[210],"bound":[211],"ratio":[214],"Poisson-Binomial":[216],"densities,":[217],"interest":[222],"potential":[225],"implications":[226],"other":[228],"combinatorial-optimization":[229],"problems.":[230],"leverage":[232],"result":[234],"design":[236],"efficient":[238],"algorithm":[240],"provides":[242],"lower-order":[244],"additive":[245],"approximation":[246],"guarantee.":[247],"validate":[249],"method":[251],"several":[253],"benchmark":[254],"datasets,":[255],"consistently":[260],"outperforms":[261],"greedy":[263],"approaches":[264],"commonly":[267],"used":[268]},"counts_by_year":[],"updated_date":"2026-04-22T08:38:42.863108","created_date":"2025-10-10T00:00:00"}