Effort Unfairness & Feature Segregation via Social Learning Hoda - PowerPoint PPT Presentation

Dec 23, 2023 •113 likes •242 views

On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness & Feature Segregation via Social Learning Hoda Heidari, Vedant Nanda, Krishna Gummadi Automated Decision Making Algorithmic Unfairness Problems with Static Notions

On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness & Feature Segregation via Social Learning Hoda Heidari, Vedant Nanda, Krishna Gummadi
Automated Decision Making
Algorithmic Unfairness
Problems with Static Notions of Fairness
Problems with Static Notions of Fairness
Problems with Static Notions of Fairness
Problems with Static Notions of Fairness
Effort Unfairness ● Economic models of Equality of Opportunity (Roemer, 2002) ● For an individual in group s ● changing a monotone feature from x to x’ ● takes effort max { 0, Q s (x') - Q s (x) }.
Long-term Impact ● Our proposal: ○ People will exert effort and invest in qualifications ○ that improve their utility (= reward - effort) . ● Individual-level model: social learning (Bandura, 1962) ○ Individuals imitate the behavior of their social models . ○ Social model is another decision subject imitating whom maximizes utility ● Population-level measure: segregation
Measuring Impact on Qualifications
Fairness Interventions
Food for Thought ● What is the ultimate purpose of a fair model? ● Are all errors created equal? ● Is it ethically acceptable ○ To incentivize different groups to obtain different qualification? ○ To employ an “unfair” model today to guarantee long-term equality? ● ...

Recommend

Auditing Machine Learning Models for Individual Bias and Unfairness Songkai Xue Department of

Auditing Machine Learning Models for Individual Bias and Unfairness Songkai Xue Department of Statistics, University of Michigan Joint work with Mikhail Yurochkin and Yuekai Sun Introduction High-stakes decision making involves Recidivism

478 views • 30 slides

An Approach for Solving the Unfairness Problem in WLANs Martin Heusse * , Yan Grunenberger * ,

An Approach for Solving the Unfairness Problem in WLANs Martin Heusse * , Yan Grunenberger * , Elena Lpez-Aguilera ** , Andrzej Duda * * LIG Grenoble Computer Laboratory ** Catalan Institute of Technology Outline WLAN unfairness problem

467 views • 22 slides

Learning Needs to Improve. OK. How? 1) The effort to

9/12/10 Current effort is to make tradiConal school perform beRer. Two problems: Learning Needs to Improve. OK. How? 1) The effort to

315 views • 5 slides

Introduction In an effort to consolidate roles & requirements the private sector needs to

Introduction In an effort to consolidate roles & requirements the private sector needs to play in a localised and sustainable market ecosystem in South Africa. Environmental and Social Governance has now become a standard feature of the

371 views • 12 slides

Local Feature Extraction and Learning for Computer Vision Part 3: Binary Feature Learning for

IEEE CVPR 2017 Tutorial on Local Feature Extraction and Learning for Computer Vision Part 3: Binary Feature Learning for Visual Recognition and Search Jiwen Lu Department of Automation, Tsinghua University, China

690 views • 50 slides

Tensor Methods for Feature Learning Anima Anandkumar U.C. Irvine Feature Learning For Efficient

Tensor Methods for Feature Learning Anima Anandkumar U.C. Irvine Feature Learning For Efficient Classification Find good transformations of input for improved classification Figures used attributed to Fei-Fei Li, Rob Fergus, Antonio Torralba,

618 views • 41 slides

Ideology Estimation, Media Slant, and Opinion Segregation: Facebook as a Social Barometer

Ideology Estimation, Media Slant, and Opinion Segregation: Facebook as a Social Barometer Keng-Chi Chang National Taiwan University 2017-09-15 1 / 57 Motivation: Bond and Messing (2015) 2 Individuals Politicians 1.5 Density 1 0.5 0

779 views • 57 slides

Physical Considerations on the Schelling model of Social Segregation Sergio Rica Universidad

Physical Considerations on the Schelling model of Social Segregation Sergio Rica Universidad Adolfo Ibez In collaboration with N. Goles-Domic and E. Goles Phys Rev E 83, 056111 (2011) On the occasion of the 60th birthday of Prof. Eric

334 views • 20 slides

Occupational segregation, poverty and race Carlos Gradn Background papers: Race and Income

Engagement on on Str Strategie ies to to Overcome In Inequali lity in in So South Afr frica 1-2 Ju June e 2017, Pret retoria, Sou outh Afr fric ica SESSION 5: PROMOTING SOCIAL MOBILITY Occupational segregation, poverty and race

534 views • 36 slides

Measuring Segregation in Social Networks Micha l Bojanowski Rense Corten ICS/Sociology,

Introduction Problem Approach Properties Measures Summary Measuring Segregation in Social Networks Micha l Bojanowski Rense Corten ICS/Sociology, Utrecht University July 2, 2010 Sunbelt XXX, Riva del Garda Introduction Problem

692 views • 40 slides

Simulating Chromosome Segregation Qi Zheng Simulating Chromosome Segregation Qi Zheng

High Performance Research Computing Simulating Chromosome Segregation Qi Zheng Simulating Chromosome Segregation Qi Zheng Department of Epidemiology & Biostatistics, Texas A&M University What motivated this study? The

211 views • 10 slides

From randomness to segregation Schelling segregation, Ising models and network cascades George

From randomness to segregation Schelling segregation, Ising models and network cascades George Barmpalias (Chinese Academy of Sciences) Richard Elwes (University of Leeds) Andy Lewis-Pye (London School of Economics) 1 More than two millennia ago,

800 views • 40 slides

Attendance Boundary Policy and the Segregation of Public Schools in the United States Tomas

Attendance Boundary Policy and the Segregation of Public Schools in the United States Tomas Monarrez UC Berkeley Oct 3rd, 2017 Racial Segregation and Schools in the United States School desegregation is one of the most ambitious social

895 views • 65 slides

Hammond and Axelrods model is not useful for studying ethnocentrism The Segregation Model

Fredrik Jansson Hammond and Axelrods model is not useful for studying ethnocentrism The Segregation Model Schelling 1971 ncase.me/polygons The Segregation Model The Segregation Model The Dissemination of Culture Model Axelrod 1997 The

589 views • 26 slides

Social Media Hub Feature The Koalas: Scarlett Taviss Aawista Chaudhry Rita Alsattah Matthew

Social Media Hub Feature The Koalas: Scarlett Taviss Aawista Chaudhry Rita Alsattah Matthew Eliot Alexander Salgo Emily Kaczmarek Feature: Social Media Notification Icons SAAM - Scenarios 1. Display notifications for multiple different

1.14k views • 17 slides

Learning Covariant Feature Detectors Karel Lenc and Andrea Vedaldi University of Oxford GMDL

Learning Covariant Feature Detectors Karel Lenc and Andrea Vedaldi University of Oxford GMDL Workshop, ECCV 2016 Local Feature Detection for Image Matching 2 (x) (x) x x ... ... The challenges of learning feature detectors

528 views • 39 slides

Rheology and Segregation Segregation of of Rheology and Granular Mixtures in Dense Flows

Rheology and Segregation Segregation of of Rheology and Granular Mixtures in Dense Flows Granular Mixtures in Dense Flows Devang Khakhar Department of Chemical Engineering Indian Institute of Technology Bombay Mumbai, India Unifying

695 views • 33 slides

Principal Component Analysis (PCA) CE-717: Machine Learning Sharif University of Technology

Principal Component Analysis (PCA) CE-717: Machine Learning Sharif University of Technology Spring 2016 Soleymani Dimensionality Reduction: Feature Selection vs. Feature Extraction Feature selection Select a subset of a given feature

5.23k views • 40 slides

Trusted Learning Environment Collegial Learning Network COLLABORATIVE EFFORT 2 Consortium for

Trusted Learning Environment Collegial Learning Network COLLABORATIVE EFFORT 2 Consortium for School Networking - CoSN 3 ABOUT CoSN Core Beliefs: Technology is a critical tool to personalize learning. Technological fluency allows

824 views • 22 slides

PCA & ICA CE-717: Machine Learning Sharif University of Technology Spring 2018 Soleymani

PCA & ICA CE-717: Machine Learning Sharif University of Technology Spring 2018 Soleymani Dimensionality Reduction: Feature Selection vs. Feature Extraction } Feature selection } Select a subset of a given feature set } Feature extraction }

875 views • 51 slides

Mach Machine Le ine Learning arning Feature Space, Feature Selection Hamid R. Rabiee Jafar

Mach Machine Le ine Learning arning Feature Space, Feature Selection Hamid R. Rabiee Jafar Muhammadi Spring 2015 http://ce.sharif.edu/courses/93-94/2/ce717-1 / Agenda Agenda Features and Patterns The Curse of Size and

731 views • 27 slides

1 The Cost of Feature Transformation Feature Rescaling } Not every transformation Input: Each

Feature Engineering } As we saw with polynomial regression, we often want to transform our data in order to get better results from a machine learning algorithm } We often get better results by: Changing how features are represented. 1. Adding

239 views • 4 slides

Self-Supervised Feature Learning by Learning to Spot Artifacts Wonbin Kim Self-Supervised

Self-Supervised Feature Learning by Learning to Spot Artifacts Wonbin Kim Self-Supervised Learning To exploit different labelings that are freely available besides or within visual data, and to use them as intrinsic reward signals to

387 views • 24 slides

Segregation and Lynching Motivation Lynching Data Measuring Lisa D. Cook Segregation Trevon

Segregation and Lynching Lisa D. Cook Trevon D. Logan John M. Parman Introduction Segregation and Lynching Motivation Lynching Data Measuring Lisa D. Cook Segregation Trevon D. Logan Results John M. Parman March 27, 2015 Segregation

419 views • 22 slides