{"id":"https://openalex.org/W2885414621","doi":"https://doi.org/10.1109/jstsp.2018.2865887","title":"Data Pre-Processing for Discrimination Prevention: Information-Theoretic Optimization and Analysis","display_name":"Data Pre-Processing for Discrimination Prevention: Information-Theoretic Optimization and Analysis","publication_year":2018,"publication_date":"2018-08-17","ids":{"openalex":"https://openalex.org/W2885414621","doi":"https://doi.org/10.1109/jstsp.2018.2865887","mag":"2885414621"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2018.2865887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2018.2865887","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","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/A5074697940","display_name":"Fl\u00e1vio P. Calmon","orcid":"https://orcid.org/0000-0002-7493-1428"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Flavio du Pin Calmon","raw_affiliation_strings":["Harvard University, Cambridge, MA, US"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, US","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103053820","display_name":"Dennis Wei","orcid":"https://orcid.org/0000-0002-6510-1537"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dennis Wei","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017540117","display_name":"Bhanukiran Vinzamuri","orcid":"https://orcid.org/0000-0003-2651-8628"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhanukiran Vinzamuri","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081874896","display_name":"Karthikeyan Natesan Ramamurthy","orcid":"https://orcid.org/0000-0002-6021-5930"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthikeyan Natesan Ramamurthy","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015286159","display_name":"Kush R. Varshney","orcid":"https://orcid.org/0000-0002-7376-5536"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kush R. Varshney","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074697940"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":3.8096,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93259074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"12","issue":"5","first_page":"1106","last_page":"1119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9550999999046326,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9269999861717224,"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/distortion","display_name":"Distortion (music)","score":0.6886283755302429},{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.6657919883728027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6632684469223022},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.5748646855354309},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.555191695690155},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5304681062698364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5010464191436768},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.48016542196273804},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.43916991353034973},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4334045648574829},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4310510754585266},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28092026710510254},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.2648787498474121},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19158142805099487}],"concepts":[{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6886283755302429},{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.6657919883728027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6632684469223022},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.5748646855354309},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.555191695690155},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5304681062698364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5010464191436768},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.48016542196273804},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43916991353034973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4334045648574829},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4310510754585266},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28092026710510254},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.2648787498474121},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19158142805099487},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2018.2865887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2018.2865887","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W21934178","https://openalex.org/W1622686296","https://openalex.org/W1988368118","https://openalex.org/W1989008275","https://openalex.org/W2014352947","https://openalex.org/W2026019770","https://openalex.org/W2035841117","https://openalex.org/W2040825624","https://openalex.org/W2055309977","https://openalex.org/W2077145963","https://openalex.org/W2096765209","https://openalex.org/W2100960835","https://openalex.org/W2110921501","https://openalex.org/W2116984840","https://openalex.org/W2118025696","https://openalex.org/W2131940723","https://openalex.org/W2136114025","https://openalex.org/W2142901448","https://openalex.org/W2147427185","https://openalex.org/W2162670686","https://openalex.org/W2166626454","https://openalex.org/W2478708596","https://openalex.org/W2496083297","https://openalex.org/W2522104760","https://openalex.org/W2524301210","https://openalex.org/W2530395818","https://openalex.org/W2540134115","https://openalex.org/W2540757487","https://openalex.org/W2558177882","https://openalex.org/W2584805976","https://openalex.org/W2624319794","https://openalex.org/W2753845591","https://openalex.org/W2949979136","https://openalex.org/W2962922665","https://openalex.org/W2962951800","https://openalex.org/W2962989257","https://openalex.org/W2963326510","https://openalex.org/W2963453196","https://openalex.org/W2963535017","https://openalex.org/W2963744072","https://openalex.org/W2964031043","https://openalex.org/W2964675004","https://openalex.org/W3005347330","https://openalex.org/W3120740533","https://openalex.org/W3126102191","https://openalex.org/W4206742934","https://openalex.org/W4236373558","https://openalex.org/W4250589301","https://openalex.org/W4285719527","https://openalex.org/W4297825594","https://openalex.org/W4299638583","https://openalex.org/W6600849757","https://openalex.org/W6636674381","https://openalex.org/W6638603156","https://openalex.org/W6654170900","https://openalex.org/W6660511875","https://openalex.org/W6674201379","https://openalex.org/W6675359311","https://openalex.org/W6676620643","https://openalex.org/W6679800425","https://openalex.org/W6684072790","https://openalex.org/W6686172355","https://openalex.org/W6696125203","https://openalex.org/W6696497002","https://openalex.org/W6727155660","https://openalex.org/W6728551298","https://openalex.org/W6729253952","https://openalex.org/W6730221699","https://openalex.org/W6738870502","https://openalex.org/W6744110554","https://openalex.org/W6765581519","https://openalex.org/W6765858885","https://openalex.org/W6773842061","https://openalex.org/W6843013015","https://openalex.org/W7018690968"],"related_works":["https://openalex.org/W2756132392","https://openalex.org/W3035814349","https://openalex.org/W4285101096","https://openalex.org/W4320477335","https://openalex.org/W2518949622","https://openalex.org/W4382725876","https://openalex.org/W2084892497","https://openalex.org/W2115614142","https://openalex.org/W2275184629","https://openalex.org/W1561889708"],"abstract_inverted_index":{"Non-discrimination":[0],"is":[1],"a":[2,14,26,31,58,73,104],"recognized":[3],"objective":[4],"in":[5,42,107],"algorithmic":[6],"decision":[7],"making.":[8],"In":[9],"this":[10],"paper,":[11],"we":[12],"introduce":[13],"novel":[15],"probabilistic":[16],"formulation":[17],"of":[18,60,63,81,114],"data":[19,32,44],"pre-processing":[20],"for":[21,29,56],"reducing":[22],"discrimination.":[23],"We":[24],"propose":[25],"convex":[27],"optimization":[28,84],"learning":[30],"transformation":[33],"with":[34,111],"three":[35],"goals:":[36],"controlling":[37],"group":[38],"discrimination,":[39],"limiting":[40],"distortion":[41],"individual":[43,115],"samples,":[45],"and":[46,69,72,77,110],"preserving":[47],"utility.":[48],"Several":[49],"theoretical":[50],"properties":[51],"are":[52,85],"established,":[53],"including":[54,89],"conditions":[55],"convexity,":[57],"characterization":[59],"the":[61,82],"impact":[62],"limited":[64],"sample":[65],"size":[66],"on":[67,91],"discrimination":[68,76,98],"utility":[70],"guarantees,":[71],"connection":[74],"between":[75],"estimation.":[78],"Two":[79],"instances":[80],"proposed":[83],"applied":[86],"to":[87],"datasets,":[88],"one":[90],"real-world":[92],"criminal":[93],"recidivism.":[94],"Results":[95],"show":[96],"that":[97],"can":[99],"be":[100],"greatly":[101],"reduced":[102],"at":[103],"small":[105],"cost":[106],"classification":[108],"accuracy":[109],"precise":[112],"control":[113],"distortion.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}