Timezone: »

A Reduction to Binary Approach for Debiasing Multiclass Datasets
Ibrahim Alabdulmohsin · Jessica Schrouff · Sanmi Koyejo

Wed Nov 30 09:30 AM -- 11:00 AM (PST) @ Hall J #332

We propose a novel reduction-to-binary (R2B) approach that enforces demographic parity for multiclass classification with non-binary sensitive attributes via a reduction to a sequence of binary debiasing tasks. We prove that R2B satisfies optimality and bias guarantees and demonstrate empirically that it can lead to an improvement over two baselines: (1) treating multiclass problems as multi-label by debiasing labels independently and (2) transforming the features instead of the labels. Surprisingly, we also demonstrate that independent label debiasing yields competitive results in most (but not all) settings. We validate these conclusions on synthetic and real-world datasets from social science, computer vision, and healthcare.

Author Information

Ibrahim Alabdulmohsin (Google)
Jessica Schrouff (DeepMind)
Jessica Schrouff

I am a Senior Research Scientist at DeepMind since 2022. I joined Alphabet in 2019 as part of Google Research working on trustworthy machine learning for healthcare. Before that, I was a postdoctoral researcher at University College London and Stanford University studying machine learning for neuroscience. My current interests lie at the intersection of trustworthy machine learning and causality.

Sanmi Koyejo (Stanford, Google Research)
Sanmi Koyejo

Sanmi Koyejo is an Assistant Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign and a research scientist at Google AI in Accra. Koyejo's research interests are in developing the principles and practice of adaptive and robust machine learning. Additionally, Koyejo focuses on applications to biomedical imaging and neuroscience. Koyejo co-founded the Black in AI organization and currently serves on its board.

More from the Same Authors