02/02/2021

Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries

Kun-Peng Ning, Lue Tao, Songcan Chen, Sheng-Jun Huang

Keywords:

Abstract Paper Similar Papers

Abstract: In addition to high accuracy, robustness is becoming increasingly important for machine learning models in various applications. Recently, much research has been devoted to improving the model robustness by training with noise perturbations. Most existing studies assume a fixed perturbation level for all training examples, which however hardly holds in real tasks. In fact, excessive perturbations may destroy the discriminative content of an example, while deficient perturbations may fail to provide helpful information for improving the robustness. Motivated by this observation, we propose to adaptively adjust the perturbation levels for each example in the training process. Specifically, a novel active learning framework is proposed to allow the model interactively querying the correct perturbation level from human experts. By designing a cost-effective sampling strategy along with a new query type, the robustness can be significantly improved with a few queries. Both theoretical analysis and experimental studies validate the effectiveness of the proposed approach.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948398
(Link will open in new window)
 0
 1
 1
 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
 2:59 
 0
 1
 0
 0
 5:06 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 12:57 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 19:57 
 0
 1
 0
 0
 4:46 
 0
 0
 0
 0
 18:32 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 13:47 
 0
 0
 0
 0
 11:24 
 0
 0
 0
 0
 13:28 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 12:01 
 0
 0
 0
 0
 6:42 
 0
 0
 0
 0
 1:32 
 0
 0
 0
 0
 3:12 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 1
 9:39 
 0
 0
 0
 0
 11:38 
 0
 0
 0
 0
 18:14 
 0
 0
 0
 0
 10:28 
 0
 0
 0
 0
 19:14 
 0
 0
 0
 0
 11:30 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 1
 4:50 
 0
 0
 0
 0
 10:37 
 0
 0
 0
 0
 8:43 
 0
 0
 0
 0
 15:18 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 10:59 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 3:24