Timezone: »

 
A Stochastic Optimization Framework for Fair Risk Minimization
Andrew Lowy · Sina Baharlouei · Rakesh Pavan · Meisam Razaviyayn · Ahmad Beirami

@
in Trustworthy and Socially Responsible Machine Learning »
Event URL: https://openreview.net/forum?id=-pP5leuRU3F »

Despite the success of large-scale empirical risk minimization (ERM) at achieving high accuracy across a variety of machine learning tasks, fair ERM is hindered by the incompatibility of fairness constraints with stochastic optimization. We consider the problem of fair classification with discrete sensitive attributes and potentially large models and data sets, requiring stochastic solvers. Existing in-processing fairness algorithms are either impractical in the large-scale setting because they require large batches of data at each iteration or they are not guaranteed to converge. In this paper, we develop the first stochastic in-processing fairness algorithm with guaranteed convergence. For demographic parity, equalized odds, and equal opportunity notions of fairness, we provide slight variations of our algorithm--called FERMI--and prove that each of these variations converges in stochastic optimization with any batch size. Empirically, we show that FERMI is amenable to stochastic solvers with multiple (non-binary) sensitive attributes and non-binary targets, performing well even with minibatch size as small as one. Extensive experiments show that FERMI achieves the most favorable tradeoffs between fairness violation and test accuracy across all tested setups compared with state-of-the-art baselines for demographic parity, equalized odds, equal opportunity. These benefits are especially significant with small batch sizes and for non-binary classification with large number of sensitive attributes, making FERMI a practical, scalable fairness algorithm.

[ Poster]  [ OpenReview]  [ Topia] 

Author Information

Andrew Lowy (USC)
Sina Baharlouei (UNIVERSITY OF SOUTHERN CALIFORNIA)
Rakesh Pavan (National Institute of Technology Karnataka)
Meisam Razaviyayn (University of Southern California)
Ahmad Beirami (Google Research)

Ahmad Beirami is a research scientist at Facebook AI, leading research to power the next generation of virtual digital assistants with AR/VR capabilities. His research broadly involves learning models with robustness and fairness considerations in large-scale systems. Prior to that, he led the AI agent research program for automated playtesting of video games at Electronic Arts. Before moving to industry in 2018, he held a joint postdoctoral fellow position at Harvard & MIT, focused on problems in the intersection of core machine learning and information theory. He is the recipient of the 2015 Sigma Xi Best PhD Thesis Award from Georgia Tech, for his work on the fundamental limits of efficient communication over IoT networks.

More from the Same Authors