SoFaiR: Single Shot Fair Representation Learning

To avoid discriminatory uses of their data, organizations can learn to map them into a representation that filters out information related to sensitive attributes. However, all existing methods in fair representation learning generate a fairness-information trade-off. To achieve different points on...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-04
Main Authors: Gitiaux, Xavier, Rangwala, Huzefa
Format: Article
Language:English
Subjects:
Distortion
Knowledge representation
Learning
Teaching methods
Tradeoffs
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To avoid discriminatory uses of their data, organizations can learn to map them into a representation that filters out information related to sensitive attributes. However, all existing methods in fair representation learning generate a fairness-information trade-off. To achieve different points on the fairness-information plane, one must train different models. In this paper, we first demonstrate that fairness-information trade-offs are fully characterized by rate-distortion trade-offs. Then, we use this key result and propose SoFaiR, a single shot fair representation learning method that generates with one trained model many points on the fairness-information plane. Besides its computational saving, our single-shot approach is, to the extent of our knowledge, the first fair representation learning method that explains what information is affected by changes in the fairness / distortion properties of the representation. Empirically, we find on three datasets that SoFaiR achieves similar fairness-information trade-offs as its multi-shot counterparts.
ISSN:2331-8422