Filters








59,325 Hits in 6.1 sec

Towards Personalized Fairness based on Causal Notion [article]

Yunqi Li, Hanxiong Chen, Shuyuan Xu, Yingqiang Ge, Yongfeng Zhang
<span title="2021-05-20">2021</span> <span class="release-stage" >pre-print</span>
However, it is important to advance from associative fairness notions to causal fairness notions for assessing fairness more properly in recommender systems.  ...  Besides, previous works on fair recommendation mainly focus on association-based fairness.  ...  Based on this, various causal-based notions have been put forward.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3404835.3462966">doi:10.1145/3404835.3462966</a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.09829v1">arXiv:2105.09829v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ruo2pftdavdv5gh3xey3crm5by">fatcat:ruo2pftdavdv5gh3xey3crm5by</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211109001245/https://arxiv.org/pdf/2105.09829v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8d/73/8d73ce9e2079987e79f0d45a068be7289a2cb152.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3404835.3462966"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.09829v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions [article]

Shira Mitchell, Eric Potash, Solon Barocas, Alexander D'Amour, Kristian Lum
<span title="2020-04-24">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A recent flurry of research activity has attempted to quantitatively define "fairness" for decisions based on statistical and machine learning (ML) predictions.  ...  In doing so, we offer a concise reference for thinking through the choices, assumptions, and fairness considerations of prediction-based decision systems.  ...  Causal definitions of fairness focus our attention on how to compensate for causal influences at decision time.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.07867v3">arXiv:1811.07867v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wfjjmcdunfe5bgo6hmz7ys6rfu">fatcat:wfjjmcdunfe5bgo6hmz7ys6rfu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827072203/https://arxiv.org/pdf/1811.07867v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6c/42/6c42489b03caa1751e2aeba4c5e081854abcccf6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.07867v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

On the Applicability of ML Fairness Notions [article]

Karima Makhlouf, Sami Zhioua, Catuscia Palamidessi
<span title="2022-03-24">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Given the inherent subjectivity of viewing the concept of fairness, several notions of fairness have been introduced in the literature.  ...  (3) fitting these two elements to recommend the most suitable fairness notion in every specific setup.  ...  Causality-based fairness notions can be used as well provided that a causal graph is available and validated by data (decision node 15).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16745v3">arXiv:2006.16745v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qtofyidn5bf45ggmnz46ya6z44">fatcat:qtofyidn5bf45ggmnz46ya6z44</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201023043558/https://arxiv.org/pdf/2006.16745v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/53/01/5301c1feb34a515458bd32bf7bffeda9a0400d0d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16745v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Fairness Amidst Non-IID Graph Data: A Literature Review [article]

Wenbin Zhang, Jeremy C. Weiss, Shuigeng Zhou, Toby Walsh
<span title="2022-02-16">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
It is therefore of great importance to bridge the traditional fairness literature designed on IID data and ubiquitous non-IID graph representations to tackle bias in ML systems.  ...  On the other hand, graphs are a ubiquitous data structure to capture connections among individual units and is non-IID by nature.  ...  The seminal work on graph based individual fairness is the notion proposed in [Kang et al., 2020] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.07170v2">arXiv:2202.07170v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b4ri7at2b5blncdgbpzbwhe6ea">fatcat:b4ri7at2b5blncdgbpzbwhe6ea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220217020415/https://arxiv.org/pdf/2202.07170v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/50/be/50be62b588d079737a9c9c8500c2957ac6c6a703.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.07170v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Causal Reasoning for Algorithmic Fairness [article]

Joshua R. Loftus, Chris Russell, Matt J. Kusner, Ricardo Silva
<span title="2018-05-15">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
fair, and give a detailed analysis of the many recent approaches to causality-based fairness.  ...  In this work, we argue for the importance of causal reasoning in creating fair algorithms for decision making.  ...  a covariate adjustment are often based on implicit causal reasoning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.05859v1">arXiv:1805.05859v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w5ouvl5cmjdtdnpgunb5vmxgrq">fatcat:w5ouvl5cmjdtdnpgunb5vmxgrq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824125554/https://arxiv.org/pdf/1805.05859v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a4/de/a4dedb26cee44e60bb641f4b4757335331d45596.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.05859v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Fairness in Recommendation: A Survey [article]

Yunqi Li, Hanxiong Chen, Shuyuan Xu, Yingqiang Ge, Juntao Tan, Shuchang Liu, Yongfeng Zhang
<span title="2022-06-01">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Recently, there has been growing attention on fairness considerations in recommender systems with more and more literature on approaches to promote fairness in recommendation.  ...  This motivates us to provide a systematic survey of existing works on fairness in recommendation. This survey focuses on the foundations for fairness in recommendation literature.  ...  [114] further defined personalized fairness based on causal notion for the collaborative filtering recommendation task.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.13619v4">arXiv:2205.13619v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/t7ycrw3vbjdyjbg53zphru6kbi">fatcat:t7ycrw3vbjdyjbg53zphru6kbi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220611075437/https://arxiv.org/pdf/2205.13619v4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/95/4b/954b3190ddf437126efcdd506466c1dafb78543d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.13619v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Legal perspective on possible fairness measures – A legal discussion using the example of hiring decisions

Marc P. Hauer, Johannes Kevekordes, Maryam Amir Haeri
<span title="">2021</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6aynyx2i45cmrgrdqsfa7jb2za" style="color: black;">Computer Law and Security Review</a> </i> &nbsp;
There are some promising approaches, but many of them are based on a "fair" ground truth, others are based on a subjective goal to be reached, which leads to the usual problem of how to define and compute  ...  and cons with regard to the respective fairness interpretation and evaluate them from a legal perspective (based on EU law).  ...  Fairness measures not based on a ground truth simply rely on a "fair" distribution of predictions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.clsr.2021.105583">doi:10.1016/j.clsr.2021.105583</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xg2pv2iek5hyresspm3dcxn56q">fatcat:xg2pv2iek5hyresspm3dcxn56q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210826134616/https://arxiv.org/pdf/2108.06918v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f9/94/f9946b3a3ce0ec93b6e7a02f4b91cecd03ee00dc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.clsr.2021.105583"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

An Introduction to Algorithmic Fairness [article]

Hilde J.P. Weerts
<span title="2021-05-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We list different types of fairness-related harms, explain two main notions of algorithmic fairness, and map the biases that underlie these harms upon the machine learning development process.  ...  These lecture notes provide an introduction to some of the core concepts in algorithmic fairness research.  ...  ., 2020] and causal modeling. Discussion As we have seen in these notes, there is no standard notion of fairness in the literature on algorithmic fairness.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.05595v1">arXiv:2105.05595v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yl4kumygmvhx7avahatuiwrh7e">fatcat:yl4kumygmvhx7avahatuiwrh7e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210514112914/https://arxiv.org/pdf/2105.05595v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/21/11/2111fc1b95c740d141865c976974f39ab0b2cfcc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.05595v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Survey on Bias and Fairness in Machine Learning [article]

Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, Aram Galstyan
<span title="2022-01-25">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Such systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that the decisions do not reflect discriminatory behavior toward certain  ...  We then created a taxonomy for fairness definitions that machine learning researchers have defined in order to avoid the existing bias in AI systems.  ...  In the context of decision-making, fairness is the absence of any prejudice or favoritism toward an individual or group based on their inherent or acquired characteristics.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.09635v3">arXiv:1908.09635v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fygrqs3sing6zdsg53t7awhih4">fatcat:fygrqs3sing6zdsg53t7awhih4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220130081201/https://arxiv.org/pdf/1908.09635v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/00/90/0090023afc66cd2741568599057f4e82b566137c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.09635v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Luck Egalitarianism, Responsibility, and Political Liberalism

RYAN LONG
<span title="2016-01-12">2016</span> <i title="Cambridge University Press (CUP)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/uv5jn2plb5cd7jwhdtlricvzhe" style="color: black;">Dialogue: Canadian Philosophical Review</a> </i> &nbsp;
A surprising consequence is that many responsibility-based objections to luck egalitarianism turn out to be objections to Rawls' political liberalism as well.  ...  Both proponents and critics assume that the theory must rely on a comprehensive conception of responsibility.  ...  On the contrary, we must appeal to causal responsibility in order to determine what amounts to fair cooperation and a fair distribution of benefits and burdens.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1017/s0012217315001110">doi:10.1017/s0012217315001110</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4c2wlx2ekrdzdcrmc77x4m6mai">fatcat:4c2wlx2ekrdzdcrmc77x4m6mai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180720164312/https://philpapers.org/archive/LONLER-2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/83/87/838707493b8bfacc8a4653d5003b7f339eed9b24.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1017/s0012217315001110"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> cambridge.org </button> </a>

Promises and Challenges of Causality for Ethical Machine Learning [article]

Aida Rahmattalabi, Alice Xiang
<span title="2022-01-26">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
notions of fairness.  ...  Specifically, we introduce causal variants of common statistical notions of fairness, and we make a novel observation that under the causal framework there is no fundamental disagreement between different  ...  Specifically, [27] provides an individual-based causal fairness definition that renders a decision fair towards an individual if it is the same in the actual world and a counterfactual world where the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.10683v1">arXiv:2201.10683v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lbsirx3pczewjeel22xpwvxtry">fatcat:lbsirx3pczewjeel22xpwvxtry</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220129215518/https://arxiv.org/pdf/2201.10683v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ed/bf/edbf580400b3db00f082fdb567bd9d7cf0efefeb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.10683v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

State of the Art in Fair ML: From Moral Philosophy and Legislation to Fair Classifiers [article]

Elias Baumann, Josef Lorenz Rumberger
<span title="2018-11-20">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However those decisions are often unfair and discriminating individuals belonging to protected groups based on race or gender.  ...  With the recent General Data Protection Regulation (GDPR) coming into effect, new awareness has been raised for such issues and with computer scientists having such a large impact on peoples lives it is  ...  An impossible example To introduce the next chapter on causal reasoning, we will construct an example based on [30, 24] with two rather different scenarios from a fairness standpoint which yet behave  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.09539v1">arXiv:1811.09539v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7e7hkumg2faffhmrgjvdxo2oiu">fatcat:7e7hkumg2faffhmrgjvdxo2oiu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191014104611/https://arxiv.org/pdf/1811.09539v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3c/bd/3cbdb3c9eb3e97a9d12d84d2b62b76884cc0003d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.09539v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

From notions of health to causality

Wim Dekkers, Bert Gordijn
<span title="2009-06-10">2009</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wompbw7ox5gn3mpdticxuh7fz4" style="color: black;">Medicine, Health care and Philosophy</a> </i> &nbsp;
From notions of health to causality 233  ...  It is based on the personal experience of one of the authors-in the role of researcher-with a woman suffering from chronic fatigue syndrome.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11019-009-9207-x">doi:10.1007/s11019-009-9207-x</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/19513814">pmid:19513814</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nkeut7do4zh3lhq2xbilleliwm">fatcat:nkeut7do4zh3lhq2xbilleliwm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180726032845/https://link.springer.com/content/pdf/10.1007%2Fs11019-009-9207-x.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/75/19/751920c87a157d9cdf07ccabc46f64ca556f5880.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11019-009-9207-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

The Zoo of Fairness metrics in Machine Learning [article]

Alessandro Castelnovo, Riccardo Crupi, Greta Greco, Daniele Regoli
<span title="2021-12-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A plethora of different definitions of fairness in ML have been proposed, that consider different notions of what is a "fair decision" in situations impacting individuals in the population.  ...  The precise differences, implications and "orthogonality" between these notions have not yet been fully analyzed in the literature.  ...  above, namely group vs. individual notions and observational vs. causality-based notions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.00467v3">arXiv:2106.00467v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xq4cmuws5zffljbawcto27izaq">fatcat:xq4cmuws5zffljbawcto27izaq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211215000515/https://arxiv.org/pdf/2106.00467v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a4/33/a433ce5af42cce118763d452d0dc16c018dd67f0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.00467v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Algorithmic Fairness in Education [article]

René F. Kizilcec, Hansol Lee
<span title="2021-04-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Statistical, similarity-based, and causal notions of fairness are reviewed and contrasted in the way they apply in educational contexts.  ...  In this introduction to algorithmic fairness in education, we draw parallels to prior literature on educational access, bias, and discrimination, and we examine core components of algorithmic systems (  ...  Causal notions of fairness Statistical and similarity-based notions of fairness are based purely on observations of random variables, but algorithmic fairness can also be approached from a causal perspective  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.05443v3">arXiv:2007.05443v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x7m3f56ybza65flnaidv3onht4">fatcat:x7m3f56ybza65flnaidv3onht4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210414051221/https://arxiv.org/ftp/arxiv/papers/2007/2007.05443.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/61/ea/61eaa2cc735b71acad839f334f34623d3b695783.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.05443v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 59,325 results