06/12/2021

A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models

Ibrahim Alabdulmohsin, Mario Lucic

Keywords: deep learning, machine learning, fairness

Abstract Paper Similar Papers

Abstract: We present a scalable post-processing algorithm for debiasing trained models, including deep neural networks (DNNs), which we prove to be near-optimal by bounding its excess Bayes risk. We empirically validate its advantages on standard benchmark datasets across both classical algorithms as well as modern DNN architectures and demonstrate that it outperforms previous post-processing methods while performing on par with in-processing. In addition, we show that the proposed algorithm is particularly effective for models trained at scale where post-processing is a natural and practical choice.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at NeurIPS 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
 2:56 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 10:07 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 13:57 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 11:35 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 3:09 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 11:28 
 0
 0
 0
 0
 13:49 
 0
 0
 0
 0
 4:30 
 0
 0
 0
 0
 18:14 
 0
 0
 0
 0
 9:34 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 17:41 
 0
 0
 0
 1
 4:35 
 0
 0
 0
 0
 5:30 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 3:30 
 0
 0
 0
 0
 12:00 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 14:40 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 3:26 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 1
 14:05 
 0
 0
 0
 0
 12:09 
 0
 0
 0
 0
 12:51 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 1
 12:45 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 14:34