{"id":"https://openalex.org/W3130088724","doi":"https://doi.org/10.1145/3442381.3449799","title":"Fair and Representative Subset Selection from Data Streams","display_name":"Fair and Representative Subset Selection from Data Streams","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3130088724","doi":"https://doi.org/10.1145/3442381.3449799","mag":"3130088724"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3449799","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449799","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3449799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yanhao Wang","orcid":null},"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":"Yanhao Wang","raw_affiliation_strings":["University of Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Francesco Fabbri","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francesco Fabbri","raw_affiliation_strings":["Pompeu Fabra University & Eurecat, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pompeu Fabra University & Eurecat, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":null,"display_name":"Michael Mathioudakis","orcid":null},"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":"Michael Mathioudakis","raw_affiliation_strings":["University of Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0722,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97525444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1340","last_page":"1350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9975000023841858,"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/T12288","display_name":"Optimization and Search Problems","score":0.9872999787330627,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/submodular-set-function","display_name":"Submodular set function","score":0.7315999865531921},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.7214000225067139},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5990999937057495},{"id":"https://openalex.org/keywords/streaming-algorithm","display_name":"Streaming algorithm","score":0.5975000262260437},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5486000180244446},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5212000012397766},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.492000013589859},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.46540001034736633},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.43869999051094055}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.7315999865531921},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.7214000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6182000041007996},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5990999937057495},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.5975000262260437},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5212000012397766},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.3449999988079071},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2827000021934509},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2556000053882599},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3442381.3449799","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449799","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.04412","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.04412","pdf_url":"https://arxiv.org/pdf/2010.04412","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:helda.helsinki.fi:10138/333087","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/333087","pdf_url":"http://hdl.handle.net/10138/333087","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":"Conference contribution"}],"best_oa_location":{"id":"doi:10.1145/3442381.3449799","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449799","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W112063162","https://openalex.org/W1680189815","https://openalex.org/W1989151913","https://openalex.org/W1997959284","https://openalex.org/W2038428842","https://openalex.org/W2061820396","https://openalex.org/W2063280781","https://openalex.org/W2119885577","https://openalex.org/W2124637492","https://openalex.org/W2141403143","https://openalex.org/W2143996311","https://openalex.org/W2144359569","https://openalex.org/W2177862760","https://openalex.org/W2223858906","https://openalex.org/W2540677289","https://openalex.org/W2592120485","https://openalex.org/W2604961496","https://openalex.org/W2757107770","https://openalex.org/W2842078607","https://openalex.org/W2963538439","https://openalex.org/W2983920042","https://openalex.org/W3008516270","https://openalex.org/W3012895300","https://openalex.org/W3033733989","https://openalex.org/W3081747061"],"related_works":[],"abstract_inverted_index":{"We":[0,92],"study":[1],"the":[2,55,61,72,98,102,119,136,161,169],"problem":[3,34,74],"of":[4,9,66,87,101,140,173],"extracting":[5],"a":[6,13,40,46,84,112,130],"small":[7],"subset":[8],"representative":[10],"items":[11,59,88],"from":[12,89],"large":[14,185],"data":[15,19,58],"stream.":[16],"In":[17,50,107],"many":[18],"mining":[20],"and":[21,30,70,145,150,171,187],"machine":[22],"learning":[23],"applications":[24],"such":[25],"as":[26,38],"social":[27],"network":[28],"analysis":[29],"recommender":[31],"systems,":[32],"this":[33,51],"can":[35],"be":[36],"formulated":[37],"maximizing":[39],"monotone":[41],"submodular":[42,104],"function":[43],"subject":[44],"to":[45,64,83,153,156],"cardinality":[47],"constraint":[48,79],"k.":[49],"work,":[52],"we":[53,109,128,167],"consider":[54],"setting":[56],"where":[57,160],"in":[60],"stream":[62,120],"belong":[63],"one":[65],"several":[67],"disjoint":[68],"groups":[69],"investigate":[71],"optimization":[73],"with":[75],"an":[76],"additional":[77],"fairness":[78],"that":[80,115,134],"limits":[81],"selection":[82],"given":[85],"number":[86],"each":[90],"group.":[91],"then":[93],"propose":[94],"efficient":[95],"algorithms":[96,176],"for":[97,121],"fairness-aware":[99],"variant":[100],"streaming":[103,132],"maximization":[105],"problem.":[106],"particular,":[108],"first":[110],"give":[111,129],"-approximation":[113],"algorithm":[114,133],"requires":[116],"passes":[117],"over":[118],"any":[122],"constant":[123],"\u03b5":[124],">":[125],"0.":[126],"Moreover,":[127],"single-pass":[131],"has":[135],"same":[137],"approximation":[138],"ratio":[139],"when":[141],"unlimited":[142],"buffer":[143,162],"sizes":[144,163],"post-processing":[146],"time":[147],"are":[148,164],"permitted,":[149],"discuss":[151],"how":[152],"adapt":[154],"it":[155],"more":[157],"practical":[158],"settings":[159],"bounded.":[165],"Finally,":[166],"demonstrate":[168],"efficiency":[170],"effectiveness":[172],"our":[174],"proposed":[175],"on":[177,184],"two":[178],"real-world":[179],"applications,":[180],"namely":[181],"maximum":[182],"coverage":[183],"graphs":[186],"personalized":[188],"recommendation.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2021-03-01T00:00:00"}