ACM FAT* 2019 Technical Program

Room: Georgia Hall 2, 3

Session Chair: Emily Denton (Google)

Translation Tutorial: A History of Quantitative Fairness in Testing

Ben Hutchinson, Margaret Mitchell

Video

Room: Georgia Hall 4, 5

Session Chair: Joshua Kroll (UC Berkeley)

Implications Tutorial: Building Community Governance of Risk Assessment

Hannah Sassaman, Reuben Jones, David Robinson.

Video

Room: Georgia Hall 7, 8

Session Chair: Ben Fish (Microsoft Research)

Hands-on Tutorial: pip install fairness: a fairness-aware classification toolkit

Sorelle Friedler, Carlos Scheidegger, Suresh Venkatasubramanian

Room: Georgia Hall 9

Session Chair: Michael Ekstrand (Boise State University)

Translation Tutorial: Values, Reflection and Engagement in Automated Decision-Making

Roel Dobbe, Morgan Ames

Room: Georgia Hall 2, 3

Session Chair: Bo Cowgill (Columbia University)

(3:00PM-3:45PM)

Invited Tutorial:
A New Era of Hate

Keegan Hankes, Swathi Shanmugasundaram
Southern Poverty Law Center (SPLC)

Video

(3:45PM-4:30PM)

Implications Tutorial: Parole denied: One Man's Fight Against a COMPAS Risk Assessment

Cynthia Conti-Cook, Glenn Rodriguez

Video

Room: Georgia Hall 4, 5

Session Chair: Luke Stark (Microsoft Research)

(3:00PM-3:45PM)

Translation Tutorial: Toward a Theory of Race for Fairness in Machine Learning

Emanuel Moss

Video

(3:45PM-4:30PM)

Translation Tutorial: Engineering for Fairness: How a Firm Conceptual Distinction between Unfairness and Bias Makes it Easier to Address Un/Fairness

Jacob Metcalf

Video

Room: Georgia Hall 7, 8

Session Chair: Aylin Caliskan (George Washington University)

Hands-on Tutorial: AI Fairness 360 (part 1)

Rachel K. E. Bellamy, Kuntal Dey, Michael Hind, Samuel Hoffman, Stephanie Houde, Kalapriya Kannan, Pranay Lohia, Jacquelyn Martino, Sameep Mehta, Aleksandra Mojsilović, Seema Nagar, Karthikeyan Natesan Ramamurthy, John T. Richards, Diptikalyan Saha, Prasanna Sattigeri, Moninder Singh, Kush Varshney, Dakuo Wang, Yunfeng Zhang

Room: Georgia Hall 9

Session Chair: Tolga Bolukbasi (Google)

Hands-on Tutorial: Measuring Unintended Bias in Text Classification Models with Real Data

Daniel Borkan, Lucas Dixon, Jeffrey Sorensen, Nithum Thain, Lucy Vasserman

Room: Georgia Hall 2, 3

Session Chair: Swati Gupta (Georgia Tech)

Translation Tutorial: Challenges of incorporating algorithmic fairness into industry practice

Henriette Cramer, Kenneth Holstein, Jennifer Wortman Vaughan, Hal Daumé III, Miroslav Dudík, Hanna Wallach, Sravana Reddy, Jean Garcia-Gathright

Video

Room: Georgia Hall 4, 5

Session Chair: Joshua Kroll (UC Berkeley)

Implications Tutorial: Reasoning About (Subtle) Biases in Data to Improve the Reliability of Decision Support Tools

Suchi Saria, Adarsh Subbaswamy

Video

Room: Georgia Hall 7, 8

Session Chair: Aylin Caliskan (George Washington University)

Hands-on Tutorial: AI Fairness 360(part 2)

Rachel K. E. Bellamy, Kuntal Dey, Michael Hind, Samuel Hoffman, Stephanie Houde, Kalapriya Kannan, Pranay Lohia, Jacquelyn Martino, Sameep Mehta, Aleksandra Mojsilović, Seema Nagar, Karthikeyan Natesan Ramamurthy, John T. Richards, Diptikalyan Saha, Prasanna Sattigeri, Moninder Singh, Kush Varshney, Dakuo Wang, Yunfeng Zhang

Room: Georgia Hall 9

Session Chair: Bo Cowgill (Columbia University)

(5:00PM-5:45PM)

Translation Tutorial: What technologists need to know about AI for international development

Craig Jolley, Shachee Doshi

Speaker: Jon Kleinberg

Fairness, Rankings, and Behavioral Biases

Many of the settings in which we seek to quantify notions of fairness and equity are based on screening decisions, where we must select from among a pool of candidates, often by ranking them. We consider how human behavioral biases can interact with the process of ranking, how we might build formal models of these biases and their effects, and what these models suggest about possible interventions. The resulting analysis provides some constructive examples of the principle that when dealing with biased agents, constraining their behavior in specific ways can sometimes both ameliorate the bias and improve the agents' performance in terms of the objectives they have set for themselves. This talk is based on joint work with Sendhil Mullainathan and Manish Raghavan.

Discussant: Jennifer Wortman Vaughan (Microsoft Research)

Session Chair: Hanna Wallach

Problem Formulation and Fairness

Samir Passi, Solon Barocas

50 Years of Test (Un)fairness: Lessons for Machine Learning

Ben Hutchinson, Margaret Mitchell

Fairness and Abstraction in Sociotechnical Systems

Andrew D. Selbst, danah boyd, Sorelle A. Friedler, Suresh Venkatasubramanian, Janet Vertesi

Session Chair: Suresh Venkatasubramanian

Who's the Guinea Pig? Investigating Online A/B/n Tests in-the-Wild

Shan Jiang, John Martin, Christo Wilson

Beyond Open vs. Closed: Balancing Individual Privacy and Public Accountability in Data Sharing

Meg Young, Luke Rodriguez, Emily Keller, Feiyang Sun, Boyang Sa, Jan Whittington, Bill Howe

Fairness-Aware Programming

Aws Albarghouthi, Samuel Vinitsky

Model Cards for Model Reporting

Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Ben Hutchinson, Elena Spitzer, Lucy Vasserman, Inioluwa Deborah Raji, Timnit Gebru

Session Chair: Carlos Castillo

Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting

Maria De-Arteaga, Alexey Romanov, Hanna Wallach, Jennifer Chayes, Christian Borgs, Alexandra Chouldechova, Sahin Geyik, Krishnaram Kenthapadi, Adam Tauman Kalai

Equality of Voice: Towards Fair Representation in Crowdsourced Top-K Recommendations

Abhijnan Chakraborty, Gourab K Patro, Niloy Ganguly, Krishna P. Gummadi, Patrick Loiseau

The Profiling Potential of Computer Vision and the Challenge of Computational Empiricism

Jake Goldenfein

An Empirical Study of Rich Subgroup Fairness for Machine Learning

Michael J. Kearns, Seth V. Neel, Aaron L. Roth, Zhiwei Steven Wu

Session Chair: Zack Lipton

Fairness through Causal Awareness: Learning Causal Latent-Variable Models for Biased Data

David Madras, Elliot Creager, Toni Pitassi, Richard Zemel

From Soft Classifiers to Hard Decisions: How fair can we be?

Ran Canetti, Aloni Cohen, Nishanth Dikkala, Govind Ramnarayan, Sarah Scheffler, Adam Smith

Deep Weighted Averaging Classifiers

Dallas Card, Michael Zhang, Noah A. Smith

Session Chair: Robin Burke

On Microtargeting Socially Divisive Ads: A Case Study of Russia-Linked Ad Campaigns on Facebook

Filipe Ribeiro, Koustuv Saha, Mahmoudreza Babaei, Lucas Henrique, Johnnatan Messias, Fabricio Benevenuto, Oana Goga, Krishna P. Gummadi, Elissa M. Redmiles

Analyzing Biases in Perception of Truth in News Stories and their Implications for Fact Checking

Mahmoudreza Babaei, Abhijnan Chakraborty, Juhi Kulshrestha, Elissa M. Redmiles, Meeyoung Cha, Krishna P. Gummadi

Controlling Polarization in Personalization: An Algorithmic Framework

L. Elisa Celis, Sayash Kapoor, Farnood Salehi, Nisheeth Vishnoi

SIREN: A Simulation Framework for Understanding the Effects of Recommender Systems in Online News Environments

Dimitrios Bountouridis, Jaron Harambam, Mykola Makhortykh, Monica Marrero, Nava Tintarev, Claudia Hauff

Session Chair: Andrew Selbst

Robot Eyes Wide Shut: Understanding Dishonest Anthropomorphism

Brenda Leong, Evan Selinger

Explaining Explanations in AI

Brent Mittelstadt, Chris Russell, Sandra Wachter

Racial categories in machine learning

Sebastian Benthall, Bruce D. Haynes

Measuring the Biases that Matter: The Ethical and Causal Foundations for Measures of Fairness in Algorithms

Bruce Glymour, Jonathan Herington

Speaker: Deirdre Mulligan

Beyond algorithmic scapegoating: fostering cultures of algorithmic responsibility through administrative law and design

Algorithmic systems and those that design and sell them are being routinely called out for the biases they embed. Yet surely organizations that purchase them, and professionals who use them share some responsibility for the algorithmic tools they choose. Through case studies this talk will explore factors that lead government agencies to acquire and use algorithmic systems that are misaligned with their goals and values, and propose two interventions to foster cultures of algorithmic responsibility in the public sector: novel uses of administrative law to police government adoption of algorithmic systems with insufficient attention to the politics they embed; and, ‘contestable’ design which publicizes values-significant parameters and settings and assists end-users in understanding and selecting them. Together these interventions cultivate skepticism, reflection, and critical engagement with algorithms in the wild, and ensure government agencies attend to values during the acquisition and deployment of algorithmic systems.

Discussant:Lilian Edwards (Newcastle University)

Session Chair: Giles Hooker

Actionable Recourse in Linear Classification

Berk Ustun, Alexander Spangher, Yang Liu

Model Reconstruction from Model Explanations

Smitha Milli, Ludwig Schmidt, Anca D. Dragan, Moritz Hardt

Efficient Search for Diverse Coherent Explanations

Chris Russell

On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection

Vivian Lai, Chenhao Tan

Session Chair: Nathan Srebro

A Moral Framework for Understanding Fair ML through Economic Models of Equality of Opportunity

Hoda Heidari, Michele Loi, Krishna Gummadi, Andreas Krause

Access to Population-Level Signaling as a Source of Inequality

Nicole Immorlica, Katrina Ligett, Juba Ziani

Fair Allocation through Competitive Equilibrium from Generic Incomes

Moshe Babaioff, Noam Nisan, Inbal Talgam-Cohen

Fair Algorithms for Learning in Allocation Problems

Hadi Elzayn, Shahin Jabbari, Christopher Jung, Michael Kearns, Seth Neel, Aaron Roth, Zachary Schutzman

Session Chair: Nicole Immorlica

Fairness under unawareness: assessing disparity when protected class is unobserved

Jiahao Chen, Nathan Kallus, Xiaojie Mao, Geoffry Svacha, Madeleine Udell

Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees

L. Elisa Celis, Lingxiao Huang, Vijay Keswani, Nisheeth K. Vishnoi

A comparative study of fairness-enhancing interventions in machine learning

Sorelle A. Friedler, Carlos Scheidegger, Suresh Venkatasubramanian, Sonam Choudhary, Evan P. Hamilton, Derek Roth

Session Chair: Karen Levy

Disparate Interactions: An Algorithm-in-the-Loop Analysis of Fairness in Risk Assessments

Ben Green, Yiling Chen

Dissecting Racial Bias in an Algorithm that Guides Health Decisions for 70 million people

Ziad Obermeyer, Sendhil Mullainathan

A Taxonomy of Ethical Tensions in Inferring Mental Health States from Social Media

Stevie Chancellor, Michael Birnbaum, Eric Caine, Vincent Silenzio, Munmun De Choudhury

Clear Sanctions, Vague Rewards: How China’s Social Credit System Defines “Good” and “Bad” ‌Behavior

Severin Engelmann, Mo Chen, Felix Fischer, Ching-yu Kao, Jens Grossklags

Session Chair: Inbal Talgam-Cohen

The Disparate Effects of Strategic Manipulation

Lily Hu, Nicole Immorlica, Jennifer Wortman Vaughan

The Social Cost of Strategic Classification

Smitha Milli, John Miller, Anca Dragan, Moritz Hardt

From Fair Decision Making To Social Equality

Hussein Mouzannar, Mesrob I. Ohannessian, Nathan Srebro

Downstream Effects of Affirmative Action

Sampath Kannan, Aaron Roth, Juba Ziani