02/02/2021

Fair Representations by Compression

Xavier Gitiaux, Huzefa Rangwala

Keywords:

Abstract Paper Similar Papers

Abstract: Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to map data into a compressed binary representation independent of sensitive attributes. We show that in an information bottleneck framework, a parsimonious representation should filter out information related to sensitive attributes if they are provided directly to the decoder. Empirical results show that the method achieves state-of-the-art accuracy-fairness trade-off and that explicit control of the entropy of the representation bit stream allows the user to move smoothly and simultaneously along both rate-distortion and rate-fairness curves.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948926
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 15:37 
 0
 0
 0
 0
 19:55 
 0
 0
 0
 0
 12:25 
 0
 0
 0
 0
 15:17 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 11:20 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 17:28 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 19:06 
 0
 0
 0
 0
 11:22 
 0
 0
 0
 0
 4:50 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 11:15 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 15:14 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 12:17 
 0
 0
 0
 0
 14:17 
 0
 0
 0
 0
 11:41 
 0
 0
 0
 0
 11:51 
 0
 0
 0
 1
 13:22 
 0
 0
 0
 0
 14:41 
 0
 0
 0
 0
 15:44 
 0
 0
 0
 0
 16:28 
 0
 0
 0
 0
 3:51 
 0
 0
 0
 0
 14:51 
 0
 0
 0
 0
 12:12 
 0
 0
 0
 0
 7:36 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 0:58 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 14:24 
 0
 0
 0
 0
 3:03 
 0
 0
 0
 0
 1:01