02/02/2021

Explaining A Black-box By Using A Deep Variational Information Bottleneck Approach

Seojin Bang, Pengtao Xie, Heewook Lee, Wei Wu, Eric Xing

Keywords:

Abstract Paper Similar Papers

Abstract: Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiveness simultaneously, leading to redundant explanations. We propose the variational information bottleneck for interpretation, VIBI, a system-agnostic interpretable method that provides a brief but comprehensive explanation. VIBI adopts an information theoretic principle, information bottleneck principle, as a criterion for finding such explanations. For each instance, VIBI selects key features that are maximally compressed about an input (briefness), and informative about a decision made by a black-box system on that input (comprehensive). We evaluate VIBI on three datasets and compare with state-of-the-art interpretable machine learning methods in terms of both interpretability and fidelity evaluated by human and quantitative metrics.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948646
(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
 11:12 
 0
 0
 0
 0
 15:09 
 0
 0
 0
 0
 15:08 
 0
 0
 0
 0
 14:02 
 0
 0
 0
 0
 10:08 
 0
 0
 0
 0
 4:16 
 0
 0
 0
 0
 11:54 
 0
 0
 0
 0
 9:54 
 0
 0
 0
 0
 12:35 
 0
 0
 0
 0
 6:36 
 0
 0
 0
 0
 6:05 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 8:54 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 15:59 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 4:45 
 0
 0
 0
 0
 12:54 
 0
 0
 0
 0
 16:23 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 10:39 
 0
 0
 0
 0
 6:13 
 0
 0
 0
 0
 4:46 
 0
 0
 0
 0
 11:48 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 16:08 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 14:06 
 0
 0
 0
 0
 13:28 
 0
 0
 0
 0
 12:03 
 0
 0
 0
 0
 12:18 
 0
 0
 0
 0
 8:11 
 0
 0
 0
 0
 18:50 
 0
 0
 0
 0
 19:29 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 11:55 
 0
 0
 0
 0
 9:51