Timezone: »

On the Importance of Architectures and Hyperparameters for Fairness in Face Recognition
Samuel Dooley · Rhea Sukthanker · John Dickerson · Colin White · Frank Hutter · Micah Goldblum
Event URL: https://openreview.net/forum?id=NpuYNxmIHrc »

Face recognition systems are used widely but are known to exhibit bias across a range of sociodemographic dimensions, such as gender and race. An array of works proposing pre-processing, training, and post-processing methods have failed to close these gaps. Here, we take a very different approach to this problem, identifying that both architectures and hyperparameters of neural networks are instrumental in reducing bias. We first run a large-scale analysis of the impact of architectures and training hyperparameters on several common fairness metrics and show that the implicit convention of choosing high-accuracy architectures may be suboptimal for fairness. Motivated by our findings, we run the first neural architecture search for fairness, jointly with a search for hyperparameters. We output a suite of models which Pareto-dominate all other competitive architectures in terms of accuracy and fairness. Furthermore, we show that these models transfer well to other face recognition datasets with similar and distinct protected attributes. We release our code and raw result files so that researchers and practitioners can replace our fairness metrics with a bias measure of their choice.

Author Information

Samuel Dooley (Department of Computer Science, University of Maryland, College Park)
Rhea Sukthanker (University of Freiburg, Albert-Ludwigs-Universität Freiburg)
John Dickerson (Arthur AI & University of Maryland)
Colin White (Abacus.AI)
Frank Hutter (University of Freiburg & Bosch)

Frank Hutter is a Full Professor for Machine Learning at the Computer Science Department of the University of Freiburg (Germany), where he previously was an assistant professor 2013-2017. Before that, he was at the University of British Columbia (UBC) for eight years, for his PhD and postdoc. Frank's main research interests lie in machine learning, artificial intelligence and automated algorithm design. For his 2009 PhD thesis on algorithm configuration, he received the CAIAC doctoral dissertation award for the best thesis in AI in Canada that year, and with his coauthors, he received several best paper awards and prizes in international competitions on machine learning, SAT solving, and AI planning. Since 2016 he holds an ERC Starting Grant for a project on automating deep learning based on Bayesian optimization, Bayesian neural networks, and deep reinforcement learning.

Micah Goldblum (University of Maryland)

More from the Same Authors