19/10/2020

Improving anchor-based explanations

Julien Delaunay, Luis Galárraga, Christine Largouët

Keywords: rule mining, discretization, machine learning, explainable ai

Abstract Paper Similar Papers

Abstract: Rule-based explanations are a popular method to understand the rationale behind the answers of complex machine learning (ML) classifiers. Recent approaches, such as Anchors, focus on local explanations based on if-then rules that are applicable in the vicinity of a target instance. This has proved effective at producing faithful explanations, yet anchor-based explanations are not free of limitations. These include long overly specific rules as well as explanations of low fidelity. This work presents two simple methods that can mitigate such issues on tabular and textual data. The first approach proposes a careful selection of the discretization method for numerical attributes in tabular datasets. The second one applies the notion of pertinent negatives to explanations on textual data. Our experimental evaluation shows the positive impact of such methods on the quality of anchor-based explanations.

The video of this talk cannot be embedded. You can watch it here:
https://dl.acm.org/doi/10.1145/3340531.3417461#sec-supp
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at CIKM 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
 18:26 
 0
 0
 0
 0
 10:16 
 0
 0
 0
 0
 10:53 
 0
 0
 0
 0
 5:14 
 0
 0
 0
 0
 3:56 
 0
 0
 0
 0
 3:08 
 0
 0
 0
 0
 12:26 
 0
 0
 0
 0
 11:55 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 1:58 
 0
 0
 0
 0
 19:08 
 0
 0
 0
 0
 12:24 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 14:06 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 2:30 
 0
 0
 0
 0
 9:52 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 12:13 
 0
 0
 0
 1
 14:03 
 0
 0
 0
 0
 13:14 
 0
 0
 0
 0
 5:46 
 0
 0
 0
 0
 12:01 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 15:06 
 0
 0
 0
 0
 28:41 
 0
 0
 0
 0
 14:07 
 0
 0
 0
 0
 16:40 
 0
 0
 0
 0
 5:55 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 10:40 
 0
 0
 0
 0
 9:41 
 0
 0
 0
 0
 13:40 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 14:39 
 0
 0
 0
 0
 13:32 
 0
 0
 0
 0
 14:16 
 0
 0
 0
 0
 3:07