12/07/2020

Deep k-NN for Noisy Labels

Dara Bahri, Heinrich Jiang, Maya Gupta

Keywords: Learning Theory

Abstract Paper Similar Papers

Abstract: Modern machine learning models are often trained on examples with noisy labels that hurt performance and are hard to identify. In this paper, we provide an empirical study showing that a simple k-nearest neighbor-based filtering approach on the logit layer of a preliminary model can remove mislabeled training data and produce more accurate models than some recently proposed methods. We also provide new statistical guarantees into its efficacy.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ICML 2020 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
 13:47 
 0
 0
 0
 0
 6:02 
 0
 0
 0
 1
 3:31 
 0
 0
 0
 0
 14:21 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 4:54 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 2:54 
 0
 0
 0
 0
 7:27 
 0
 0
 0
 0
 3:04 
 0
 0
 0
 0
 4:25 
 0
 0
 0
 0
 19:30 
 0
 0
 0
 0
 12:01 
 0
 0
 0
 0
 4:46 
 0
 0
 0
 0
 14:24 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 14:37 
 0
 0
 0
 0
 12:25 
 0
 0
 0
 0
 14:24 
 0
 0
 0
 0
 12:42 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 5:13 
 0
 0
 0
 0
 14:11 
 0
 0
 0
 0
 10:59 
 0
 0
 0
 0
 10:41 
 0
 0
 0
 0
 5:24 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 5:17 
 0
 0
 0
 0
 2:46 
 1
 1
 0
 0
 5:46 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 19:29 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 13:10 
 0
 0
 0
 0
 3:52 
 0
 0
 0
 0
 2:51 
 0
 0
 0
 0
 8:28 
 0
 0
 0
 0
 12:31