All sessions, including the poster session, will take place in Suite 202 of the World Trade and Convention Center, 1800 Argyle Street, Halifax, NS, Canada.
Please note that the workshop starts at 8:15AM, not 8:00AM or 8:50AM, as incorrectly listed on the conference website, program, and app.
Suresh Venkatasubramanian
Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English – Su Lin Blodgett and Brendan O’Connor
Fair Clustering Through Fairlets – Flavio Chierichetti, Ravi Kumar, Silvio Lattanzi and Sergei Vassilvitskii
Calibrated Fairness in Bandits – Yang Liu, Goran Radanovic, Christos Dimitrakakis, David Parkes and Debmalya Mandal
The Authority of ‘Fair’ in Machine Learning – Michael Skirpan and Micha Gorelick
"The Seen and Unseen Factors Influencing Knowledge in AI Systems"
Posters include:
A reductions approach to fair classification – Alekh Agarwal, Alina Beygelzimer, Miroslav Dudik and John Langford
Interpretability via Model Extraction – Osbert Bastani, Carolyn Kim and Hamsa Bastani
Learning Fair Classifiers: A Regularization Approach – Yahav Bechavod and Katrina Ligett
A Convex Framework for Fair Regression – Richard Berk, Hoda Heidari, Shahin Jabbari, Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel and Aaron Roth
Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations – Alex Beutel, Jilin Chen, Zhe Zhao and Ed H. Chi
Fair Pipelines – Amanda Bower, Sarah Kitchen, Laura Niss, Martin Strauss, Alexander Vargo and Suresh Venkatasubramanian
Multisided Fairness for Recommendation – Robin Burke
Fair Personalization – L. Elisa Celis and Nisheeth Vishnoi
Fairer and more accurate, but for whom? – Alexandra Chouldechova and Max G'Sell
Decoupled classifiers for fair and efficient ML – Cynthia Dwork, Nicole Immorlica, Adam Kalai and Max Leiserson
Decision making with limited feedback: Error bounds for recidivism prediction and predictive policing – Danielle Ensign, Sorelle Friedler, Scott Neville, Carlos Scheidegger and Suresh Venkatasubramanian
Is it ethical to avoid error analysis? – Eva García-Martín and Niklas Lavesson
On Fairness, Diversity and Randomness in Algorithmic Decision Making – Nina Grgic-Hlaca, Muhammad Bilal Zafar, Krishna P. Gummadi and Adrian Weller
Better Fair Algorithms for Contextual Bandits – Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel and Aaron Roth
Fair Algorithms for Infinite Contextual Bandits – Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel and Aaron Roth
Interpretable & Explorable Approximations of Black Box Models – Himabindu Lakkaraju, Ece Kamar, Rich Caruana and Jure Leskovec
Discriminatory Transfer – Chao Lan and Jun Huan
The causal impact of bail on case outcomes for indigent defendants – Kristian Lum and Mike Baiocchi
Causal Falling Rule Lists – Fulton Wang and Cynthia Rudin
New Fairness Metrics for Recommendation that Embrace Differences – Sirui Yao and Bert Huang
Identifying Significant Predictive Bias in Classifiers – Zhe Zhang and Daniel Neill
"Friends Don't Let Friends Deploy Black Box Models: Preventing Bias via Transparent Machine Learning"
Runaway Feedback Loops in Predictive Policing – Danielle Ensign, Sorelle A. Friedler, Scott Neville, Carlos Scheidegger and Suresh Venkatasubramanian
Fairness at Equilibrium in the Labor Market – Lily Hu and Yiling Chen
Preference vs. Parity-based Notions of Fairness – Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, Krishna P. Gummadi and Adrian Weller
Logics and Practices of Transparency and Opacity in Real-world Applications of Public Sector Machine Learning – Michael Veale