Timezone: »

 
Poster
Fairness without Demographics through Adversarially Reweighted Learning
Preethi Lahoti · Alex Beutel · Jilin Chen · Kang Lee · Flavien Prost · Nithum Thain · Xuezhi Wang · Ed Chi

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #867

Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fairness concerns. However, in practice factors like privacy and regulation often preclude the collection of protected features, or their use for training or inference, severely limiting the applicability of traditional fairness research. Therefore, we ask: How can we train a ML model to improve fairness when we do not even know the protected group memberships? In this work we address this problem by proposing Adversarially Reweighted Learning (ARL). In particular, we hypothesize that non-protected features and task labels are valuable for identifying fairness issues, and can be used to co-train an adversarial reweighting approach for improving fairness. Our results show that ARL improves Rawlsian Max-Min fairness, with notable AUC improvements for worst-case protected groups in multiple datasets, outperforming state-of-the-art alternatives.

Author Information

Preethi Lahoti (Max Planck Institute for Informatics, Germany)

Preethi Lahoti is a fourth-year IMPRS doctoral candidate at Max Planck Institute for Informatics (Germany), co-supervised by Prof. Gerhard Weikum and Prof. Krishna Gummadi. She is primarily interested in building responsible, trustworthy, and well-founded machine learning systems. Preethi has a M.Sc. in Machine Learning from Aalto University (Finland), and a B.E. in Computer Science from Osmania University (India). During her studies, she has done research internships at Google Brain (U.S.A) and Nokia Bell Labs (Ireland). Previously, she was an engineer at Microsoft from 2012 to 2015, contributing to a variety of products including core ranking and relevance for Bing.

Alex Beutel (Google)
Jilin Chen (Google Brain)
Kang Lee (Google Research)
Flavien Prost (Google)
Nithum Thain (Google)
Xuezhi Wang (Google)
Ed Chi (Google Inc.)

d H. Chi is a Principal Scientist at Google, leading several machine learning research teams focusing on neural modeling, inclusive ML, reinforcement learning, and recommendation systems in Google Brain team. He has delivered significant improvements for YouTube, News, Ads, Google Play Store at Google with >325 product launches in the last 6 years. With 39 patents and over 120 research articles, he is also known for research on user behavior in web and social media. Prior to Google, he was the Area Manager and a Principal Scientist at Palo Alto Research Center's Augmented Social Cognition Group, where he led the team in understanding how social systems help groups of people to remember, think and reason. Ed completed his three degrees (B.S., M.S., and Ph.D.) in 6.5 years from University of Minnesota. Recognized as an ACM Distinguished Scientist and elected into the CHI Academy, he recently received a 20-year Test of Time award for research in information visualization. He has been featured and quoted in the press, including the Economist, Time Magazine, LA Times, and the Associated Press. An avid swimmer, photographer and snowboarder in his spare time, he also has a blackbelt in Taekwondo.

More from the Same Authors