no code implementations • 25 Jun 2022 • David Munechika, Zijie J. Wang, Jack Reidy, Josh Rubin, Krishna Gade, Krishnaram Kenthapadi, Duen Horng Chau
Recent research has developed algorithms for effectively identifying intersectional bias in the form of interpretable, underperforming subsets (or slices) of the data.
no code implementations • 15 Feb 2021 • Aalok Shanbhag, Avijit Ghosh, Josh Rubin
Predictions are the currency of a machine learning model, and to understand the model's behavior over segments of a dataset, or over time, is an important problem in machine learning research and practice.