fairness

Fairness Christos Dimitrakakis October 3, 2019 . . . . . . . - PowerPoint PPT Presentation

Jun 08, 2023 •164 likes •989 views

Fairness Christos Dimitrakakis October 3, 2019 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 1 / 41 Fairness definitions

  1. Fairness Christos Dimitrakakis October 3, 2019 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 1 / 41

  2. Fairness definitions Fairness What is it? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 2 / 41

  3. Fairness definitions Fairness What is it? ▶ Meritocracy. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 2 / 41

  4. Fairness definitions Fairness What is it? ▶ Meritocracy. ▶ Proportionality and representation. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 2 / 41

  5. Fairness definitions Fairness What is it? ▶ Meritocracy. ▶ Proportionality and representation. ▶ Equal treatment. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 2 / 41

  6. Fairness definitions Fairness What is it? ▶ Meritocracy. ▶ Proportionality and representation. ▶ Equal treatment. ▶ Non-discrimination. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 2 / 41

  7. Fairness definitions Meritocracy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 3 / 41

  8. Fairness definitions Meritocracy Example 1 (College admissions) ▶ Student A has a grade 4/5 from Gota Highschool. ▶ Student B has a grade 5/5 from Vasa Highschool. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 3 / 41

  9. Fairness definitions Meritocracy Example 1 (College admissions) ▶ Student A has a grade 4/5 from Gota Highschool. ▶ Student B has a grade 5/5 from Vasa Highschool. Example 2 (Additional information) ▶ 70% of admitted Gota graduates with 4+ get their degree. ▶ 50% of admitted Vasa graduates with 5 get their degree. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 3 / 41

  10. Fairness definitions Meritocracy Example 1 (College admissions) ▶ Student A has a grade 4/5 from Gota Highschool. ▶ Student B has a grade 5/5 from Vasa Highschool. Example 2 (Additional information) ▶ 70% of admitted Gota graduates with 4+ get their degree. ▶ 50% of admitted Vasa graduates with 5 get their degree. We still don’t know how a specific student will do! Solutions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 3 / 41

  11. Fairness definitions Meritocracy Example 1 (College admissions) ▶ Student A has a grade 4/5 from Gota Highschool. ▶ Student B has a grade 5/5 from Vasa Highschool. Example 2 (Additional information) ▶ 70% of admitted Gota graduates with 4+ get their degree. ▶ 50% of admitted Vasa graduates with 5 get their degree. We still don’t know how a specific student will do! Solutions ▶ Admit everybody? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 3 / 41

  12. Fairness definitions Meritocracy Example 1 (College admissions) ▶ Student A has a grade 4/5 from Gota Highschool. ▶ Student B has a grade 5/5 from Vasa Highschool. Example 2 (Additional information) ▶ 70% of admitted Gota graduates with 4+ get their degree. ▶ 50% of admitted Vasa graduates with 5 get their degree. We still don’t know how a specific student will do! Solutions ▶ Admit everybody? ▶ Admit randomly? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 3 / 41

  13. Fairness definitions Meritocracy Example 1 (College admissions) ▶ Student A has a grade 4/5 from Gota Highschool. ▶ Student B has a grade 5/5 from Vasa Highschool. Example 2 (Additional information) ▶ 70% of admitted Gota graduates with 4+ get their degree. ▶ 50% of admitted Vasa graduates with 5 get their degree. We still don’t know how a specific student will do! Solutions ▶ Admit everybody? ▶ Admit randomly? ▶ Use prediction of individual academic performance? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 3 / 41

  14. Fairness definitions Proportional representation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 4 / 41 https:

  15. Fairness definitions Hiring decisions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 5 / 41

  16. Fairness definitions Fairness and information Example 3 (College admissions data) School Male Female A 62% 82% B 63% 68% C 37% 34% D 33% 35% E 28% 24% F 6% 7% Average 45% 38% . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 6 / 41

  17. Fairness in machine learning Bail decisions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 7 / 41

  18. Fairness in machine learning Bail decisions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 7 / 41

  19. Fairness in machine learning Bail decisions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 7 / 41

  20. Fairness in machine learning Bail decisions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 7 / 41

  21. Fairness in machine learning Bail decisions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 7 / 41

  22. Fairness in machine learning Bail decisions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 7 / 41

  23. Fairness in machine learning Bail decisions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 7 / 41

  24. Fairness in machine learning Whites get lower scores than blacks 1 600 600 500 500 Count Count 400 400 300 300 200 200 100 100 0 0 1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10 Risk Score Risk Score Black White Figure: Apparent bias in risk scores towards black versus white defendants. 1 Pro-publica, 2016 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 8 / 41

  25. Fairness in machine learning But scores equally accurately predict recidivsm 2 Figure: Recidivism rates by risk score. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 9 / 41 2 Washington Post, 2016

  26. Fairness in machine learning But non-offending blacks get higher scores Figure: Score breakdown based on recidivism rates. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 10 / 41

  27. Fairness in machine learning Graphical models and independence ▶ Why is it not possible to be fair in all respects? ▶ Different notions of conditional independence. ▶ Can only be satisfied rarely simultaneously. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 11 / 41

  28. Graphical models Graphical models x 2 x 1 x 3 Figure: Graphical model (directed acyclic graph) for three variables. Joint probability Let x = ( x 1 , . . . , x n ). Then x : Ω → X , X = ∏ i X i and: P ( x ∈ A ) = P ( { ω ∈ Ω | x ( ω ) ∈ A } ) . Factorisation P ( x ) = P ( x B | x C ) P ( x C ) , B , C ⊂ [ n ] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . C. Dimitrakakis Fairness October 3, 2019 12 / 41

Recommend

Fairness in Machine Learning Fairness in Supervised Learning Make decisions by machine learning:

Fairness in Machine Learning Fairness in Supervised Learning Make decisions by machine learning:

Fairness in Machine Learning Fairness in Supervised Learning Make decisions by machine learning: Software can make decision free of human biases Fairness in Supervised Learning Make decisions by machine learning: Software is

501 views • 46 slides
On Combining State Space Reductions with Global Fairness Assumptions Shaojie Zhang 1 Jun Sun 2 Jun

On Combining State Space Reductions with Global Fairness Assumptions Shaojie Zhang 1 Jun Sun 2 Jun

Background & Motivation Model Checking with Global Fairness Symmetry Reduction & Global Fairness Partial Order Reduction & Global Fairness Summary On Combining State Space Reductions with Global Fairness Assumptions Shaojie Zhang 1

402 views • 25 slides
Media Fairness, Diversity 1 Outline Fairness (case studies, basic definitions) Diversity

Media Fairness, Diversity 1 Outline Fairness (case studies, basic definitions) Diversity

Online Social Networks and Media Fairness, Diversity 1 Outline Fairness (case studies, basic definitions) Diversity An experiment on the diversity of Facebook 2 Fairness, Non-discrimination To discriminate is to treat someone

1.03k views • 99 slides
Fairness in Machine Learning: Part I Privacy & Fairness in Data Science CS848 Fall 2019

Fairness in Machine Learning: Part I Privacy & Fairness in Data Science CS848 Fall 2019

Fairness in Machine Learning: Part I Privacy & Fairness in Data Science CS848 Fall 2019 Outline High Level View Recap Supervised Learning: Binary Classification Survey of Approaches to Fairness in Supervised Learning Warmup:

593 views • 35 slides
COMP30112: Concurrency Topics 5.4: Fairness and Starvation Howard Barringer Room KB2.20: email:

COMP30112: Concurrency Topics 5.4: Fairness and Starvation Howard Barringer Room KB2.20: email:

Topic 5.4: Fairness and Starvation COMP30112: Concurrency Topics 5.4: Fairness and Starvation Howard Barringer Room KB2.20: email: Howard.Barringer@manchester.ac.uk April 2008 Topic 5.4: Fairness and Starvation Outline Topic 5.4: Fairness

785 views • 20 slides
HOW CAN FAIRNESS OPINIONS PROVIDE VALUE TO SHAREHOLDERS? 4th OIV International Business Valuation

HOW CAN FAIRNESS OPINIONS PROVIDE VALUE TO SHAREHOLDERS? 4th OIV International Business Valuation

HOW CAN FAIRNESS OPINIONS PROVIDE VALUE TO SHAREHOLDERS? 4th OIV International Business Valuation Conference 30 November 2015 Milan, Italy Jay E. Fishman, FASA Jfishman@finresearch.com 1 WHAT IS A FAIRNESS OPINION? A fairness opinion is

484 views • 36 slides
UAS in Collision Investigation Lieutenant J. Teachout Officer B. Kleinberg Integrity Fairness

UAS in Collision Investigation Lieutenant J. Teachout Officer B. Kleinberg Integrity Fairness

UAS in Collision Investigation Lieutenant J. Teachout Officer B. Kleinberg Integrity Fairness Excellence Pix4d Capture UAV/Setting Selection Integrity Fairness Excellence Setting Grid Integrity Fairness Excellence Start

309 views • 7 slides
ETHICS & FAIRNESS IN AI- ETHICS & FAIRNESS IN AI- ENABLED SYSTEMS ENABLED SYSTEMS

ETHICS & FAIRNESS IN AI- ETHICS & FAIRNESS IN AI- ENABLED SYSTEMS ENABLED SYSTEMS

ETHICS & FAIRNESS IN AI- ETHICS & FAIRNESS IN AI- ENABLED SYSTEMS ENABLED SYSTEMS Christian Kaestner (with slides from Eunsuk Kang) Required reading: R. Caplan, J. Donovan, L. Hanson, J. Matthews. " Algorithmic Accountability:

1.42k views • 75 slides
Fairness in ML 2: Equal opportunity and odds Privacy & Fairness in Data Science CS848 Fall

Fairness in ML 2: Equal opportunity and odds Privacy & Fairness in Data Science CS848 Fall

Fairness in ML 2: Equal opportunity and odds Privacy & Fairness in Data Science CS848 Fall 2019 Slides adapted from https://fairmlclass.github.io/4.html 2 Outline Recap: Disparity impact Issues with Disparate Impact

5.56k views • 35 slides
Fairness in Machine Learning: Practicum Privacy & Fairness in Data Science CS848 Fall 2019

Fairness in Machine Learning: Practicum Privacy & Fairness in Data Science CS848 Fall 2019

Fairness in Machine Learning: Practicum Privacy & Fairness in Data Science CS848 Fall 2019 Human Decision Making Suppose we want to recommend a movie. Data Decision Maker Decision Jane likes Bollywood musicals. Bob: You should

3.14k views • 26 slides
Fairness issues in new large scale parallel platforms. Denis TRYSTRAM LIG Universit de

Fairness issues in new large scale parallel platforms. Denis TRYSTRAM LIG Universit de

Fairness issues in new large scale parallel platforms. Fairness issues in new large scale parallel platforms. Denis TRYSTRAM LIG Universit de Grenoble Alpes Inria Institut Universitaire de France july 15, 2015 Fairness issues in new

700 views • 56 slides
On fairness in theorem proving Maria Paola Bonacina Dipartimento di Informatica Universit` a

On fairness in theorem proving Maria Paola Bonacina Dipartimento di Informatica Universit` a

Outline Motivation Uniform fairness for saturation Fairness for theorem proving Discussion On fairness in theorem proving Maria Paola Bonacina Dipartimento di Informatica Universit` a degli Studi di Verona Verona, Italy, EU Talk given at

728 views • 39 slides
Flow Rate Fairness: Dismantling a Religion Bob Briscoe presented by Brighten Godfrey 1 Fairness

Flow Rate Fairness: Dismantling a Religion Bob Briscoe presented by Brighten Godfrey 1 Fairness

Flow Rate Fairness: Dismantling a Religion Bob Briscoe presented by Brighten Godfrey 1 Fairness in networks Flow rate equality! 911 Easily circumvented Doesnt even optimize for any metric of interest hotornot.com Fig. 1:

484 views • 17 slides
Fairness and Reciprocity Armin Falk University of Zurich, CESifo, CEPR, IZA Berkeley, August

Fairness and Reciprocity Armin Falk University of Zurich, CESifo, CEPR, IZA Berkeley, August

Fairness and Reciprocity Armin Falk University of Zurich, CESifo, CEPR, IZA Berkeley, August 2002 Armin Falk, University of Zurich 1 Overview Why deal with fairness? Fairness and reciprocity in the lab Bilateral games

865 views • 65 slides
Fairness and Reciprocity Michele Albach March 26th, 2019 Questions to Answer What does it mean

Fairness and Reciprocity Michele Albach March 26th, 2019 Questions to Answer What does it mean

Fairness and Reciprocity Michele Albach March 26th, 2019 Questions to Answer What does it mean to act fairly? When do people act fairly? What games exhibit fairness? Why do people act fairly? What factors affect fairness?

651 views • 34 slides
FAIRNESS RISK MEASURES FAIRNESS RISK MEASURES Robert C. Williamson Aditya Menon LOSS FUNCTIONS

FAIRNESS RISK MEASURES FAIRNESS RISK MEASURES Robert C. Williamson Aditya Menon LOSS FUNCTIONS

FAIRNESS RISK MEASURES FAIRNESS RISK MEASURES Robert C. Williamson Aditya Menon LOSS FUNCTIONS - OUTCOME CONTINGENT UTILITIES LOSS FUNCTIONS - OUTCOME CONTINGENT UTILITIES Walds abstraction: a loss function : Y A + {+

919 views • 79 slides
Model and parameter identification through Bayesian inference in solid mechanics Hussein Rappel

Model and parameter identification through Bayesian inference in solid mechanics Hussein Rappel

Model and parameter identification through Bayesian inference in solid mechanics Hussein Rappel h.rappel@gmail.com September 07, 2018 Hussein Rappel (UL-ULg) BI for parameter identification September 07, 2018 1 / 69 Introduction:

789 views • 78 slides
STILLWATER AVENUE BIKEWAY MEETING June 27, 2017 Luke Hanson City of Saint Paul, Public Works

STILLWATER AVENUE BIKEWAY MEETING June 27, 2017 Luke Hanson City of Saint Paul, Public Works

STILLWATER AVENUE BIKEWAY MEETING June 27, 2017 Luke Hanson City of Saint Paul, Public Works Stillwater Ave Bikeway Tonights Agenda: Present information on what is being proposed Answer Questions and talk to City Staff Get

500 views • 20 slides
MPE inference in Conditional Linear Gaussian Networks Antonio Salmern 1 Rafael Rum 1 Helge

MPE inference in Conditional Linear Gaussian Networks Antonio Salmern 1 Rafael Rum 1 Helge

MPE inference in Conditional Linear Gaussian Networks Antonio Salmern 1 Rafael Rum 1 Helge Langseth 2 Anders L. Madsen 3 , 4 Thomas D. Nielsen 4 1 Dept. Mathematics, University of Almera, Spain 2 Dept. Computer and Information Science.

860 views • 38 slides
Pri Primar mary y On One e Cu Curr rriculum iculum P Presenta esentation tion Our

Pri Primar mary y On One e Cu Curr rriculum iculum P Presenta esentation tion Our

Kinde nderK rKare re El Element mentary y Schoo hool The Best st Sta tart t In Life Pri Primar mary y On One e Cu Curr rriculum iculum P Presenta esentation tion Our School Curriculum Our curriculum promotes lifelong

653 views • 22 slides
Basic Redesign Group Project Bad design principles of existing webpage ___ Bad Design

Basic Redesign Group Project Bad design principles of existing webpage ___ Bad Design

Basic Redesign Group Project Bad design principles of existing webpage ___ Bad Design Principles of existing webpage 1. No negative space to make the different elements appear clearly Example from Five second test Questions: What did you

482 views • 24 slides
Deep Generative Modelling 1. Introduction 2. Background 3. Approach 4. Results 5. Ongoing Work

Deep Generative Modelling 1. Introduction 2. Background 3. Approach 4. Results 5. Ongoing Work

Archit Sharma (14129) Project Presentation for CS772A Abhinav Agrawal (14011) Anubhav Shrivastava (14114) Deep Generative Modelling 1. Introduction 2. Background 3. Approach 4. Results 5. Ongoing Work 1 Table of contents Introduction

601 views • 21 slides
Presentation Template This deck is a workbook designed to help you complete the project. Please

Presentation Template This deck is a workbook designed to help you complete the project. Please

Design X Social Challenge 2020 Presentation Template This deck is a workbook designed to help you complete the project. Please follow the instructions provided in each slide. IMPORTANT INSTRUCTIONS: If you have a Google account, sign in

379 views • 15 slides
PHILIPPINE AGRICULTURAL ENGINEERING STANDARD PAES 102 : 2000 Foreword This standard is a

PHILIPPINE AGRICULTURAL ENGINEERING STANDARD PAES 102 : 2000 Foreword This standard is a

PHILIPPINE AGRICULTURAL ENGINEERING STANDARD PAES 102 : 2000 Foreword This standard is a revision of the Standard Administrative Order (SAO) 399:1980 Operator Manuals and Technical Publications for Agricultural Tractors and

414 views • 15 slides

More recommend