@inproceedings{8b622b1dcf1f44f581c3cb95ef4286a0,
title = "Null it out: Guarding protected attributes by iterative nullspace projection",
abstract = "The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models. We present Iterative Null-space Projection (INLP), a novel method for removing information from neural representations. Our method is based on repeated training of linear classifiers that predict a certain property we aim to remove, followed by projection of the representations on their null-space. By doing so, the classifiers become oblivious to that target property, making it hard to linearly separate the data according to it. While applicable for multiple uses, we evaluate our method on bias and fairness use-cases, and show that our method is able to mitigate bias in word embeddings, as well as to increase fairness in a setting of multi-class classification.",
author = "Shauli Ravfogel and Yanai Elazar and Hila Gonen and Michael Twiton and Yoav Goldberg",
note = "Publisher Copyright: {\textcopyright} 2020 Association for Computational Linguistics; 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 ; Conference date: 05-07-2020 Through 10-07-2020",
year = "2020",
month = jan,
day = "1",
language = "الإنجليزيّة",
series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",
pages = "7237--7256",
booktitle = "ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",
address = "الولايات المتّحدة",
}