International Business Machines Corporation

University of Michigan

Moulinath Banerjee

Sohini Upadhyay

Mikhail Yurochkin

Yuekai Sun

Debarghya Mukherjee

The present invention provides techniques for learning Mahalanobis distance similarity metrics from data for individually fair machine learning models. In one aspect, a method for learning a fair Mahalanobis distance similarity metric includes: obtaining data with similarity annotations; selecting, based on the data obtained, a model for learning a Mahalanobis covariance matrix Σ; and learning the Mahalanobis covariance matrix Σ from the data using the model selected, wherein the Mahalanobis covariance matrix Σ fully defines the fair Mahalanobis distance similarity metric.

Growing community of inventors

Portage, MI, United States of America

Moulinath Banerjee