Abstract: 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 ?; and learning the Mahalanobis covariance matrix ? from the data using the model selected, wherein the Mahalanobis covariance matrix ? fully defines the fair Mahalanobis distance similarity metric.

Abstract: Obtain a first data set, a second data set, and a machine learning model. Construct a sensitive subspace of the first data set that defines a fair metric for distance among elements of the first data set. Fairly train the machine learning model on the first data set using a distributionally robust optimization approach based on the fair metric. Produce an individually fair set of labels by applying the fairly trained machine learning model to the second data set. Allocate a resource according to the individually fair set of labels.

Abstract: Finding the space spanned by user profiles of consumed items for making recommendations commences by first estimating a mean and covariance for a set of labeled items associated with a profile. Thereafter, a vector is identified that belongs to a convex cone spanned by the user profiles based on the estimated mean and covariance, the labels and items. The labels are mirrored in a negative space defined by the identified vector. The weighted covariance matrix is computed based on the mirrored labels; and eigenvalues and eigenvectors are computed of the weighted covariance matrix. A first set of eigenvalues share a value and wherein a remainder of the eigenvalues correspond to eigenvectors that span the profile.