The Impossibility Theorem of Machine Fairness -- A Causal Perspective

With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exist in society and propagated them to the future through their decisions. There a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
1. Verfasser:	Saravanakumar, Kailash Karthik
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Learning Statistics - Machine Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title
container_volume
creator	Saravanakumar, Kailash Karthik
description	With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exist in society and propagated them to the future through their decisions. There are three prominent metrics of machine fairness used in the community, and it has been shown statistically that it is impossible to satisfy them all at the same time. This has led to an ambiguity with regards to the definition of fairness. In this report, a causal perspective to the impossibility theorem of fairness is presented along with a causal goal for machine fairness.
doi_str_mv	10.48550/arxiv.2007.06024
format	Article
fullrecord	<record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2007_06024</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2007_06024</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-1f296643b4625fd7673d36c8465c0220a7ba60b7715d3be350d18c7e47ba115d3</originalsourceid><addsrcrecordid>eNotz71uwjAUhmEvDBX0AjrVN-D0xL_piCJokajaIXt07JwISwmJbIrK3Rdop096hk96GXsqodCVMfCC6SeeCwngCrAg9QPbNAfiu3Geco4-DvF04VeZEo186vkHhkM8Et9iTEfKmQvB17zG74wD_6KUZwqneKYVW_Q4ZHr83yVrtpumfhf7z7ddvd4LtE6Lspev1mrltZWm75x1qlM2VNqaAFICOo8WvHOl6ZQnZaArq-BIX7282ZI9_93eO9o5xRHTpb31tPce9Qu9AUO2</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>The Impossibility Theorem of Machine Fairness -- A Causal Perspective</title><source>arXiv.org</source><creator>Saravanakumar, Kailash Karthik</creator><creatorcontrib>Saravanakumar, Kailash Karthik</creatorcontrib><description>With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exist in society and propagated them to the future through their decisions. There are three prominent metrics of machine fairness used in the community, and it has been shown statistically that it is impossible to satisfy them all at the same time. This has led to an ambiguity with regards to the definition of fairness. In this report, a causal perspective to the impossibility theorem of fairness is presented along with a causal goal for machine fairness.</description><identifier>DOI: 10.48550/arxiv.2007.06024</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2020-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2007.06024$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2007.06024$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Saravanakumar, Kailash Karthik</creatorcontrib><title>The Impossibility Theorem of Machine Fairness -- A Causal Perspective</title><description>With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exist in society and propagated them to the future through their decisions. There are three prominent metrics of machine fairness used in the community, and it has been shown statistically that it is impossible to satisfy them all at the same time. This has led to an ambiguity with regards to the definition of fairness. In this report, a causal perspective to the impossibility theorem of fairness is presented along with a causal goal for machine fairness.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71uwjAUhmEvDBX0AjrVN-D0xL_piCJokajaIXt07JwISwmJbIrK3Rdop096hk96GXsqodCVMfCC6SeeCwngCrAg9QPbNAfiu3Geco4-DvF04VeZEo186vkHhkM8Et9iTEfKmQvB17zG74wD_6KUZwqneKYVW_Q4ZHr83yVrtpumfhf7z7ddvd4LtE6Lspev1mrltZWm75x1qlM2VNqaAFICOo8WvHOl6ZQnZaArq-BIX7282ZI9_93eO9o5xRHTpb31tPce9Qu9AUO2</recordid><startdate>20200712</startdate><enddate>20200712</enddate><creator>Saravanakumar, Kailash Karthik</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20200712</creationdate><title>The Impossibility Theorem of Machine Fairness -- A Causal Perspective</title><author>Saravanakumar, Kailash Karthik</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-1f296643b4625fd7673d36c8465c0220a7ba60b7715d3be350d18c7e47ba115d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Saravanakumar, Kailash Karthik</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Saravanakumar, Kailash Karthik</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The Impossibility Theorem of Machine Fairness -- A Causal Perspective</atitle><date>2020-07-12</date><risdate>2020</risdate><abstract>With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exist in society and propagated them to the future through their decisions. There are three prominent metrics of machine fairness used in the community, and it has been shown statistically that it is impossible to satisfy them all at the same time. This has led to an ambiguity with regards to the definition of fairness. In this report, a causal perspective to the impossibility theorem of fairness is presented along with a causal goal for machine fairness.</abstract><doi>10.48550/arxiv.2007.06024</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.48550/arxiv.2007.06024
ispartof
issn
language	eng
recordid	cdi_arxiv_primary_2007_06024
source	arXiv.org
subjects	Computer Science - Artificial Intelligence Computer Science - Learning Statistics - Machine Learning
title	The Impossibility Theorem of Machine Fairness -- A Causal Perspective
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T19%3A41%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=The%20Impossibility%20Theorem%20of%20Machine%20Fairness%20--%20A%20Causal%20Perspective&rft.au=Saravanakumar,%20Kailash%20Karthik&rft.date=2020-07-12&rft_id=info:doi/10.48550/arxiv.2007.06024&rft_dat=%3Carxiv_GOX%3E2007_06024%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true