Fair Meta-Learning: Learning How to Learn Fairly
Abstract
Data sets for fairness relevant tasks can lack examples or be biased according to a specific label in a sensitive attribute. We demonstrate the usefulness of weight based meta-learning approaches in such situations. For models that can be trained through gradient descent, we demonstrate that there are some parameter configurations that allow models to be optimized from a few number of gradient steps and with minimal data which are both fair and accurate. To learn such weight sets, we adapt the popular MAML algorithm to Fair-MAML by the inclusion of a fairness regularization term. In practice, Fair-MAML allows practitioners to train fair machine learning models from only a few examples when data from related tasks is available. We empirically exhibit the value of this technique by comparing to relevant baselines.
Cite
@article{arxiv.1911.04336,
title = {Fair Meta-Learning: Learning How to Learn Fairly},
author = {Dylan Slack and Sorelle Friedler and Emile Givental},
journal= {arXiv preprint arXiv:1911.04336},
year = {2019}
}
Comments
arXiv admin note: substantial text overlap with arXiv:1908.09092