{"id":"https://openalex.org/W3121950587","doi":"https://doi.org/10.1145/3398730.3399194","title":"Fairness-Aware Instrumentation of Preprocessing~Pipelines for Machine Learning","display_name":"Fairness-Aware Instrumentation of Preprocessing~Pipelines for Machine Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3121950587","doi":"https://doi.org/10.1145/3398730.3399194","mag":"3121950587"},"language":"en","primary_location":{"id":"pmh:oai:dare.uva.nl:openaire/4fd0b3d5-941e-47ec-9563-11ef9c563d2c","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/fairnessaware-instrumentation-of-preprocessing-pipelines-for-machine-learning(4fd0b3d5-941e-47ec-9563-11ef9c563d2c).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yang, K, Huang, B, Stoyanovich, J & Schelter, S 2020, Fairness-Aware Instrumentation of Preprocessing Pipelines for Machine Learning. in HILDA 2020 : Workshop on Human-In-the-Loop Data Analytics : co-located with SIGMOD 2020 : 19 June 2020, Portland, OR, USA., 9, Workshop on Human-In-the-Loop Data Analytics, Portland, Oregon, United States, 19/06/20. < https://ssc.io/publication/fairness-aware-instrumentation-of-preprocessing-pipelines-forml-hilda20/ >","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://handle.uba.uva.nl/personal/pure/en/publications/fairnessaware-instrumentation-of-preprocessing-pipelines-for-machine-learning(4fd0b3d5-941e-47ec-9563-11ef9c563d2c).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061285256","display_name":"Ke Yang","orcid":"https://orcid.org/0000-0002-1617-5986","observed_orcids":["https://orcid.org/0000-0002-1617-5986"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Yang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1617-5986","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109486409","display_name":"Biao Huang","orcid":"https://orcid.org/0000-0001-9082-2216","observed_orcids":["https://orcid.org/0000-0001-9082-2216"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082830839","display_name":"Julia Stoyanovich","orcid":"https://orcid.org/0000-0002-1587-0450","observed_orcids":["https://orcid.org/0000-0002-1587-0450"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julia Stoyanovich","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1587-0450","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090934117","display_name":"Sebastian Schelter","orcid":"https://orcid.org/0000-0003-4722-5840","observed_orcids":["https://orcid.org/0000-0003-4722-5840"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Schelter","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4722-5840","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6309,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94610497,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9502000212669373,"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":0.9502000212669373,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.018400000408291817,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.003000000026077032,"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/algorithmic-fairness","display_name":"algorithmic fairness","score":0.875},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.5339999794960022},{"id":"https://openalex.org/keywords/directed-acyclic-graphs","display_name":"directed acyclic graphs","score":0.8809999823570251},{"id":"https://openalex.org/keywords/protected-groups","display_name":"protected groups","score":0.7300000190734863},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.5580000281333923},{"id":"https://openalex.org/keywords/open-source-library","display_name":"open-source library","score":0.5709999799728394},{"id":"https://openalex.org/keywords/data-representativeness","display_name":"data representativeness","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.818829357624054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6929835677146912},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6517136096954346},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.6260839700698853},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.5882330536842346},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5635496377944946},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5580617189407349},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5409480333328247},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.495342880487442},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.474072128534317},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.45455870032310486},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4254753887653351},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41874009370803833},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.41802626848220825},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35553276538848877},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18096378445625305},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1791800856590271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.117267906665802},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:dare.uva.nl:openaire/4fd0b3d5-941e-47ec-9563-11ef9c563d2c","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/fairnessaware-instrumentation-of-preprocessing-pipelines-for-machine-learning(4fd0b3d5-941e-47ec-9563-11ef9c563d2c).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yang, K, Huang, B, Stoyanovich, J & Schelter, S 2020, Fairness-Aware Instrumentation of Preprocessing Pipelines for Machine Learning. in HILDA 2020 : Workshop on Human-In-the-Loop Data Analytics : co-located with SIGMOD 2020 : 19 June 2020, Portland, OR, USA., 9, Workshop on Human-In-the-Loop Data Analytics, Portland, Oregon, United States, 19/06/20. < https://ssc.io/publication/fairness-aware-instrumentation-of-preprocessing-pipelines-forml-hilda20/ >","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/4fd0b3d5-941e-47ec-9563-11ef9c563d2c","doi":null,"is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/fairnessaware-instrumentation-of-preprocessing-pipelines-for-machine-learning(4fd0b3d5-941e-47ec-9563-11ef9c563d2c).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"HILDA 2020: Workshop on Human-In-the-Loop Data Analytics : co-located with SIGMOD 2020 : 19 June 2020, Portland, OR, USA","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"mag:3121950587","doi":"https://doi.org/10.1145/3398730.3399194","is_oa":false,"landing_page_url":"https://par.nsf.gov/biblio/10182459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/4fd0b3d5-941e-47ec-9563-11ef9c563d2c","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/fairnessaware-instrumentation-of-preprocessing-pipelines-for-machine-learning(4fd0b3d5-941e-47ec-9563-11ef9c563d2c).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yang, K, Huang, B, Stoyanovich, J & Schelter, S 2020, Fairness-Aware Instrumentation of Preprocessing Pipelines for Machine Learning. in HILDA 2020 : Workshop on Human-In-the-Loop Data Analytics : co-located with SIGMOD 2020 : 19 June 2020, Portland, OR, USA., 9, Workshop on Human-In-the-Loop Data Analytics, Portland, Oregon, United States, 19/06/20. < https://ssc.io/publication/fairness-aware-instrumentation-of-preprocessing-pipelines-forml-hilda20/ >","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.7578999996185303,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"sustainable_development_goals_aurora":[{"score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2006447892","https://openalex.org/W2586577420","https://openalex.org/W2613597870","https://openalex.org/W2948130259","https://openalex.org/W2989755645","https://openalex.org/W2996282314","https://openalex.org/W3110197861","https://openalex.org/W3123374861"],"related_works":["https://openalex.org/W4210354100","https://openalex.org/W3194157648","https://openalex.org/W3173683037","https://openalex.org/W4414789757","https://openalex.org/W7155579999","https://openalex.org/W4387294395","https://openalex.org/W4398229873","https://openalex.org/W4413360471","https://openalex.org/W6962793470","https://openalex.org/W4402993176"],"abstract_inverted_index":{"Surfacing":[0],"and":[1,36,41,73,82],"mitigating":[2],"bias":[3,35],"in":[4,30,60,79],"ML":[5,109],"pipelines":[6,62,70],"is":[7],"a":[8,12],"complex":[9],"topic,":[10],"with":[11,71,85,104],"dire":[13],"need":[14],"to":[15,19,26,32,37,76,87],"provide":[16],"system-level":[17],"support":[18],"data":[20,39,58,80,93],"scientists.":[21],"Humans":[22],"should":[23],"be":[24],"empowered":[25],"debug":[27],"these":[28],"pipelines,":[29],"order":[31],"control":[33],"for":[34,63],"improve":[38],"quality":[40],"representativeness.":[42],"We":[43,98],"propose":[44],"fair-DAGs,":[45],"an":[46],"open-source":[47],"library":[48,66],"that":[49],"extracts":[50],"directed":[51],"acyclic":[52],"graph":[53],"(DAG)":[54],"representations":[55],"of":[56,102],"the":[57,69,92,96,100],"flow":[59],"preprocessing":[61],"ML.":[64],"The":[65],"subsequently":[67],"instruments":[68],"tracing":[72],"visualization":[74],"code":[75],"capture":[77],"changes":[78],"distributions":[81],"identify":[83],"distortions":[84],"respect":[86],"protected":[88],"group":[89],"membership":[90],"as":[91],"travels":[94],"through":[95],"pipeline.":[97],"illustrate":[99],"utility":[101],"fair-DAGs":[103],"experiments":[105],"on":[106],"publicly":[107],"available":[108],"pipelines.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-02-01T00:00:00"}