{"id":"https://openalex.org/W2947657760","doi":"https://doi.org/10.1145/3292500.3330987","title":"Clustering without Over-Representation","display_name":"Clustering without Over-Representation","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2947657760","doi":"https://doi.org/10.1145/3292500.3330987","mag":"2947657760"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330987","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330987","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330987","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330987","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070799139","display_name":"Sara Ahmadian","orcid":"https://orcid.org/0000-0002-7060-6775"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sara Ahmadian","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037972828","display_name":"Alessandro Epasto","orcid":"https://orcid.org/0000-0003-0456-3217"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alessandro Epasto","raw_affiliation_strings":["Google Research, Google Research, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Google Research, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101772779","display_name":"Ravi Kumar","orcid":"https://orcid.org/0000-0002-2203-2586"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Kumar","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018777906","display_name":"Mohammad Mahdian","orcid":"https://orcid.org/0000-0001-6294-0039"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Mahdian","raw_affiliation_strings":["Google Research, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google Research, New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070799139"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":6.6544,"has_fulltext":true,"cited_by_count":79,"citation_normalized_percentile":{"value":0.9732802,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"267","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9948999881744385,"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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9948999881744385,"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/T10057","display_name":"Face and Expression Recognition","score":0.9905999898910522,"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/T12541","display_name":"Graph Labeling and Dimension Problems","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8599127531051636},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.6379213929176331},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.6253909468650818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6095729470252991},{"id":"https://openalex.org/keywords/rounding","display_name":"Rounding","score":0.6063828468322754},{"id":"https://openalex.org/keywords/k-medians-clustering","display_name":"k-medians clustering","score":0.5384374260902405},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.53347247838974},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5229129195213318},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.48373177647590637},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.46114498376846313},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.43467479944229126},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42739158868789673},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40969792008399963},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34446972608566284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3426439166069031},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3106514811515808}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8599127531051636},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.6379213929176331},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.6253909468650818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6095729470252991},{"id":"https://openalex.org/C136625980","wikidata":"https://www.wikidata.org/wiki/Q663208","display_name":"Rounding","level":2,"score":0.6063828468322754},{"id":"https://openalex.org/C115328559","wikidata":"https://www.wikidata.org/wiki/Q4041956","display_name":"k-medians clustering","level":5,"score":0.5384374260902405},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.53347247838974},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5229129195213318},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.48373177647590637},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.46114498376846313},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.43467479944229126},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42739158868789673},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40969792008399963},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34446972608566284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3426439166069031},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3106514811515808},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3292500.3330987","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330987","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330987","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.12753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.12753","pdf_url":"https://arxiv.org/pdf/1905.12753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330987","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330987","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330987","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2947657760.pdf","grobid_xml":"https://content.openalex.org/works/W2947657760.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1516407653","https://openalex.org/W1836068669","https://openalex.org/W1961345416","https://openalex.org/W1970776799","https://openalex.org/W1973264045","https://openalex.org/W1983197449","https://openalex.org/W1999341643","https://openalex.org/W2011430131","https://openalex.org/W2014352947","https://openalex.org/W2040825624","https://openalex.org/W2073583237","https://openalex.org/W2097246321","https://openalex.org/W2100960835","https://openalex.org/W2112429379","https://openalex.org/W2154851992","https://openalex.org/W2396394641","https://openalex.org/W2544318541","https://openalex.org/W2785893262","https://openalex.org/W2788795195","https://openalex.org/W2807790463","https://openalex.org/W2901801762","https://openalex.org/W2912019195","https://openalex.org/W2953289765","https://openalex.org/W2962771056","https://openalex.org/W2962951800","https://openalex.org/W2963308332","https://openalex.org/W2963916887","https://openalex.org/W2963919086","https://openalex.org/W2963992001","https://openalex.org/W2970788251","https://openalex.org/W3104097132","https://openalex.org/W3120740533","https://openalex.org/W3169457211"],"related_works":["https://openalex.org/W3146523624","https://openalex.org/W2160785859","https://openalex.org/W2241871771","https://openalex.org/W3140018618","https://openalex.org/W2407786351","https://openalex.org/W2555816786","https://openalex.org/W3011266291","https://openalex.org/W1990996020","https://openalex.org/W2390610678","https://openalex.org/W2188840951"],"abstract_inverted_index":{"In":[0],"this":[1,81],"paper":[2],"we":[3,83,128],"consider":[4],"clustering":[5,27,48,52,151],"problems":[6],"in":[7,39,51,125,148],"which":[8],"each":[9],"point":[10],"is":[11,18,37,44,61,65,95],"endowed":[12],"with":[13,30,135],"a":[14,99,103,130],"color.":[15],"The":[16],"goal":[17],"to":[19,23],"cluster":[20],"the":[21,25,31,56,76,108,112,116],"points":[22],"minimize":[24],"classical":[26],"cost":[28],"but":[29],"additional":[32],"constraint":[33],"that":[34,67,87,143],"no":[35,68,119],"color":[36,57,120],"over-represented":[38],"any":[40,73,126],"cluster.":[41,74],"This":[42],"problem":[43,117],"motivated":[45],"by":[46],"practical":[47],"settings,":[49],"e.g.,":[50],"news":[53,70],"articles":[54],"where":[55,118],"of":[58,80,91,115],"an":[59,85,122],"article":[60],"its":[62],"source,":[63],"it":[64],"preferable":[66],"single":[69],"source":[71],"dominates":[72],"For":[75,111],"most":[77],"general":[78],"version":[79],"problem,":[82],"obtain":[84,129],"algorithm":[86,94,133],"has":[88,121],"provable":[89,136],"guarantees":[90],"performance;":[92],"our":[93,144],"based":[96],"on":[97,139],"finding":[98,149],"fractional":[100],"solution":[101,109],"using":[102],"linear":[104],"program":[105],"and":[106],"rounding":[107],"subsequently.":[110],"special":[113],"case":[114],"absolute":[123],"majority":[124],"cluster,":[127],"simpler":[131],"combinatorial":[132],"also":[134],"guarantees.":[137],"Experiments":[138],"real-world":[140],"data":[141],"shows":[142],"algorithms":[145],"are":[146],"effective":[147],"good":[150],"without":[152],"over-representation.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}