bias and fairness in ai ml models
play

Bias and Fairness in AI/ML models Swati Gupta Assistant Professor - PowerPoint PPT Presentation

Sep 11, 2022 •3.41k likes •3.92k views

Bias and Fairness in AI/ML models Swati Gupta Assistant Professor School of Industrial and Systems Engineering, Georgia Institute of Technology October 25, 2018 Digital Data Flows Master Class: Emerging Technologies Machine Learning

  1. Bias and Fairness in 
 AI/ML models Swati Gupta Assistant Professor School of Industrial and Systems Engineering, Georgia Institute of Technology October 25, 2018 Digital Data Flows Master Class: Emerging Technologies

  2. Machine Learning Pipeline 2 Machine Data driven Data Learning/AI decisions What is the effect of these decisions on human well-being? Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | Source for images: Google images, iStock.

  3. What is Bias/Fairness? 3 “Bias. When scientific or technological decisions are based on a narrow set of systemic, structural or social concepts and norms , the resulting technology can privilege certain groups and harm others.” – Nature comment Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  4. What is Bias/Fairness? 3 “Bias. When scientific or technological decisions are based on a narrow set of systemic, structural or social concepts and norms , the resulting technology can privilege certain groups and harm others.” – Nature comment Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  5. 4 Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  6. 4 Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  7. 4 Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  8. 4 Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  9. Outline of the talk 5 � Bias in the data, models and variables � Fairness Metrics � Statistical measures � Equity measures � Trolley Problem of Choice Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  10. [Lum, Isaac, 2016] Predictive Policing 6 “application of analytical techniques to identify likely targets for police intervention and prevent crime or solve past crimes by making statistical predictions” Heat map of drug arrests made Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  11. ML finds patterns in data 7 Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  12. ML finds patterns in data 7 Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  13. PredPol: crime type, time, loc 8 [Kristian Lum, William Isaac, 2016] Heat map of drug arrests made Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  14. Not just about collection 9 We live in a biased society, so it’s inevitable that data collected about that We live in a biased society, so it’s inevitable that data collected about that society will be biased: inherent bias, test data, feedback, proxies.. society will be biased: inherent bias, test data, feedback, proxies.. Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  15. Not just about collection 9 We live in a biased society, so it’s inevitable that data collected about that We live in a biased society, so it’s inevitable that data collected about that society will be biased: inherent bias, test data, feedback, proxies.. society will be biased: inherent bias, test data, feedback, proxies.. Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  16. Not just about collection 9 We live in a biased society, so it’s inevitable that data collected about that We live in a biased society, so it’s inevitable that data collected about that society will be biased: inherent bias, test data, feedback, proxies.. society will be biased: inherent bias, test data, feedback, proxies.. “We also found that setting the gender to female resulted in getting fewer instances of an ad related to high paying jobs than setting it to male. “ Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  17. Not just about collection 9 We live in a biased society, so it’s inevitable that data collected about that We live in a biased society, so it’s inevitable that data collected about that society will be biased: inherent bias, test data, feedback, proxies.. society will be biased: inherent bias, test data, feedback, proxies.. Proxies : predicting crime using data on arrests , Not on incidence of crime . We do not want such biases to propagate into systems that make life-changing decisions. Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  18. Outline of the talk 10 � Bias in the data, models and variables � Fairness Metrics � Statistical measures � Equity measures � Trolley Problem of Choice Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  19. Machine Learning Pipeline 11 Machine Data driven Data Learning/AI decisions What is the effect of these decisions on human well-being? Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | Source of images: Google images, iStock.

  20. Classification 12 Hired for job or not, will re-offend or not (prison), given a loan or not. YES NO Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  21. Statistical Definitions of Fairness 13 Hired for job or not, will re-offend or not (prison), given a loan or not. YES Is it fair to achieve highest accuracy in classification? NO Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | ProPublica, May 2016

  22. Statistical Definitions of Fairness 13 Hired for job or not, will re-offend or not (prison), given a loan or not. YES Is it fair to achieve highest accuracy in classification? NO COMPAS Risk Score: ProPublica Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | ProPublica, May 2016

  23. Statistical Definitions of Fairness 13 Hired for job or not, will re-offend or not (prison), given a loan or not. YES Is it fair to achieve highest accuracy in classification? NO COMPAS Risk Score: ProPublica Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | ProPublica, May 2016

  24. Statistical Definitions of Fairness 13 Hired for job or not, will re-offend or not (prison), given a loan or not. YES Is it fair to achieve highest accuracy in classification? Or is it fair to balance false positives across the groups? NO Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | ProPublica, May 2016

  25. Statistical Definitions of Fairness 13 Hired for job or not, will re-offend or not (prison), given a loan or not. YES Is it fair to achieve highest accuracy in classification? Or is it fair to balance false positives across the groups? NO Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | ProPublica, May 2016

  26. Statistical Definitions of Fairness 14 Hired for job or not, will re-offend or not (prison), given a loan or not. YES Is it fair to achieve highest accuracy in classification? Or is it fair to balance false positives across the groups? False negatives ? NO Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | Wikipedia

  27. Statistical Definitions of Fairness 14 In fact, different stakeholders might have different points of view Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | Wikipedia

  28. Equity Metrics of Fairness 15 What about general decisions: how much loan to give ? where to place an emergency room ? Where to schedule deliveries? distance Group A Group B Is it fair to minimize total distance travelled by any group? Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  29. Equity Metrics of Fairness 16 What about general decisions: how much loan to give ? where to place an emergency room ? Where to schedule deliveries? Group A Group B Is it fair to minimize total distance travelled by any group? Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  30. Equity Metrics of Fairness 16 What about general decisions: how much loan to give ? where to place an emergency room ? Where to schedule deliveries? Group A Group B Is it fair to minimize total distance travelled by any group? Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  31. Equity Metrics of Fairness 17 What about general decisions: how much loan to give ? where to place an emergency room ? Where to schedule deliveries? Group A Group B Is it fair to minimize average distance travelled by any group (per person)? Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  32. Equity Metrics of Fairness 17 What about general decisions: how much loan to give ? where to place an emergency room ? Where to schedule deliveries? Group A Group B Group by race ? income ? insurance ? Is it fair to minimize average distance travelled by any group (per person)? Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

  33. Equity Metrics of Fairness 18 Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology | Marsh and Schilling 1993

  34. Outline of the talk 19 � Bias in the data, models and variables � Fairness Metrics � Statistical measures � Equity measures � Trolley Problem of Choice Bias and Fairness in AI/ML models | Swati Gupta | Georgia Institute of Technology

Recommend

Bias and Fairness in Machine Learning Irene Y. Chen @irenetrampoline

Bias and Fairness in Machine Learning Irene Y. Chen @irenetrampoline

Bias and Fairness in Machine Learning Irene Y. Chen @irenetrampoline http://gendershades.org/overview.html https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing COMPAS Correctional Offender Management

918 views • 48 slides
Bias, Fairness, Accountability, and Transparency in Machine Learning CS 115 Computing for the

Bias, Fairness, Accountability, and Transparency in Machine Learning CS 115 Computing for the

Bias, Fairness, Accountability, and Transparency in Machine Learning CS 115 Computing for the Socio-Techno Web Instructor: Brian Brubach Announcements Adjustment to deadline schedule Assignment 5 due Tuesday Project milestone 4 due

845 views • 22 slides
Machine Learning 2 DS 4420 - Spring 2020 Bias and fairness Byron C. Wallace Material in this

Machine Learning 2 DS 4420 - Spring 2020 Bias and fairness Byron C. Wallace Material in this

Machine Learning 2 DS 4420 - Spring 2020 Bias and fairness Byron C. Wallace Material in this lecture modified from materials created by Jay Alammar (http://jalammar.github.io/ illustrated-transformer/) and Sasha Rush

1.6k views • 79 slides
Controlling Fairness and Bias in Dynamic Learning-to-Rank ACM SIGIR 2020 Marco Morik * ,

Controlling Fairness and Bias in Dynamic Learning-to-Rank ACM SIGIR 2020 Marco Morik * ,

Controlling Fairness and Bias in Dynamic Learning-to-Rank ACM SIGIR 2020 Marco Morik * , Ashudeep Singh * , Jessica Hong , Thorsten Joachims TU Berlin, Cornell University Dynamic Learning-to-Rank +1 +1 +1 +1 +1 1 2

224 views • 20 slides
Bias reduction in the estimation of Rasch models Outline David Firth 1 Rasch Models 1

Bias reduction in the estimation of Rasch models Outline David Firth 1 Rasch Models 1

Rasch Models Maximum likelihood estimation Bias reduction Parameterization Application Discussion References Bias reduction in the estimation of Rasch models Outline David Firth 1 Rasch Models 1 d.firth@warwick.ac.uk Ioannis Kosmidis 21

77 views • 7 slides
Social bias and fairness in NLP GAIA Conference 2020 Olof Mogren, PhD RISE Research Institutes

Social bias and fairness in NLP GAIA Conference 2020 Olof Mogren, PhD RISE Research Institutes

Social bias and fairness in NLP GAIA Conference 2020 Olof Mogren, PhD RISE Research Institutes of Sweden Natural language processing (NLP) A field of research. Language data : language: a kind of protocol for inter-human communication;

231 views • 19 slides
BIAS What Is Bias? Bias can be defined as favoring one side, position, or belief being

BIAS What Is Bias? Bias can be defined as favoring one side, position, or belief being

BIAS What Is Bias? Bias can be defined as favoring one side, position, or belief being partial or prejudiced Where have you seen bias? Bias vs. Propaganda Bias is prejudice; a preconceived judgment or an opinion formed

717 views • 29 slides
Bias reduction in generalized nonlinear models Ioannis Kosmidis and David Firth Department of

Bias reduction in generalized nonlinear models Ioannis Kosmidis and David Firth Department of

Bias reduction in generalized nonlinear models Ioannis Kosmidis and David Firth Department of Statistics JSM 2009 Reduction of the bias Generalized nonlinear models Illustration Generalized linear models Outline Reduction of the bias 1

395 views • 17 slides
Fairness and bias in Machine Learning A quick review on tools to detect biases in machine

Fairness and bias in Machine Learning A quick review on tools to detect biases in machine

QCon 2019 Fairness and bias in Machine Learning A quick review on tools to detect biases in machine learning model Thierry Silbermann, Tech Lead Data Science at Nubank thierry.silbermann@nubank.com.br Data collection Todays

870 views • 45 slides
Equity & Excellence: Hidden Bias Implicit Bias Inherent Bias

Equity & Excellence: Hidden Bias Implicit Bias Inherent Bias

Equity & Excellence: Hidden Bias Implicit Bias Inherent Bias ____________________________________________ Vincent R. De Lucia Educator-in-Residence Director of Mandatory Training & PD New Jersey School Boards Association Anderson

426 views • 41 slides
Fairness and Transparency in Ranking Carlos Castillo / UPF chato@acm.org Data and Algorithmic

Fairness and Transparency in Ranking Carlos Castillo / UPF chato@acm.org Data and Algorithmic

Fairness and Transparency in Ranking Carlos Castillo / UPF chato@acm.org Data and Algorithmic Bias Workshop (DAB) at CIKM'18 Turin, Italy, 2018-10-22 Ranking in IR Objective : provide maximum relevance to searche r Order by decreasing

1.01k views • 62 slides
bad decision bias? 2 5 6 Affinity Bias: What can we do? 2. 3. 1. Seek

bad decision bias? 2 5 6 Affinity Bias: What can we do? 2. 3. 1. Seek

bad decision bias? 2 5 6 Affinity Bias: What can we do? 2. 3. 1. Seek outputs Compare rather than Be aware performance compentenci not people es 7 9 10 11 12 Unconscious bias refers to a

292 views • 15 slides
BIAS BIAS LIGHT LIGHT & & MEDIUM MEDIUM TR TRUCK UCK TIRES TIRES Bias Bias Ligh

BIAS BIAS LIGHT LIGHT & & MEDIUM MEDIUM TR TRUCK UCK TIRES TIRES Bias Bias Ligh

BIAS BIAS LIGHT LIGHT & & MEDIUM MEDIUM TR TRUCK UCK TIRES TIRES Bias Bias Ligh ight T t Truck / / Trail iler r Ti Tire Si Size No Nome mencla latu ture 9.50-16 9.50 16.5L .5LT/D T/D ST ST 7.00 7.00-15 15 1 10

121 views • 11 slides
Bias in, Bias out: Gender Equality and the Fourth Industrial Revolution Debra Howcroft and

Bias in, Bias out: Gender Equality and the Fourth Industrial Revolution Debra Howcroft and

Bias in, Bias out: Gender Equality and the Fourth Industrial Revolution Debra Howcroft and Jill Rubery Work and Equalities Institute University of Manchester Bias in, bias out: an overview Two parts Identify the methodology

706 views • 21 slides
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

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
History-alignment Models for Bias-aware Prediction of Virological Response to HIV Combination

History-alignment Models for Bias-aware Prediction of Virological Response to HIV Combination

History-alignment Models for Bias-aware Prediction of Virological Response to HIV Combination Therapy Jasm ina Bogojeska Department of C omputational Biology and Applied Algorithmics, Max-Planck Institute for Informatics AR E VIR G

171 views • 13 slides
Expectancy bias and Bias and forensic evidence Bias and speech research forensic speech

Expectancy bias and Bias and forensic evidence Bias and speech research forensic speech

Overview Bias effects Expectancy bias and Bias and forensic evidence Bias and speech research forensic speech research Blind forensic speech research Maartje Schreuder TMFI / Maastricht University I AFPA 2011 Bundeskrim

180 views • 7 slides
Implicit Bias Implicit bias Implicit bias refers to attitudes or stereotypes that affect our

Implicit Bias Implicit bias Implicit bias refers to attitudes or stereotypes that affect our

Implicit Bias Implicit bias Implicit bias refers to attitudes or stereotypes that affect our understanding, actions and decisions in an unconscious manner. It's different from suppressed thoughts we might conceal to keep the peace; it's

634 views • 16 slides
Invertible Generative Models for Inverse Problems Mitigating Representation Error and Dataset Bias

Invertible Generative Models for Inverse Problems Mitigating Representation Error and Dataset Bias

Invertible Generative Models for Inverse Problems Mitigating Representation Error and Dataset Bias M. Asim, M. Daniels, O. Leong, P . Hand, A. Ahmed Inverse Problems with Generative Models as Image Priors Inverse Problems with Generative Models

369 views • 22 slides
Inductive Bias: How to generalize on novel data CS 478 - Inductive Bias 1 Non-Linear Tasks l

Inductive Bias: How to generalize on novel data CS 478 - Inductive Bias 1 Non-Linear Tasks l

Inductive Bias: How to generalize on novel data CS 478 - Inductive Bias 1 Non-Linear Tasks l Linear Regression will not generalize well to the task below l Needs a non-linear surface Could use one or our future models l Could also do a

356 views • 33 slides
Using Hierarchical Models to Calibrate Selection Bias Douglas Rivers Stanford University and

Using Hierarchical Models to Calibrate Selection Bias Douglas Rivers Stanford University and

Using Hierarchical Models to Calibrate Selection Bias Douglas Rivers Stanford University and YouGov February 26, 2016 Margins of error We agree that margin of sampling error in surveys has an accepted meaning and that this measure is not

564 views • 20 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:

1.41k views • 75 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
Robust Models in Information Retrieval Nedim Lipka Benno Stein Bauhaus-Universitt Weimar

Robust Models in Information Retrieval Nedim Lipka Benno Stein Bauhaus-Universitt Weimar

Robust Models in Information Retrieval Nedim Lipka Benno Stein Bauhaus-Universitt Weimar [www.webis.de] Robust Models in Information Retrieval Outline Introduction Bias and Variance Robust Models in IR Summary Excursus: Bias

821 views • 51 slides

More recommend