19/10/2020

ALEX: Active learning based enhancement of a classification model’s EXplainability

Ishani Mondal, Debasis Ganguly

Keywords: image classification, model interpretability, active learning

Abstract Paper Similar Papers

Abstract: An active learning (AL) algorithm seeks to construct an effective classifier with a minimal number of labeled examples in a bootstrapping manner. While standard AL heuristics, such as selecting those points for annotation for which a classification model yields least confident predictions, there has been no empirical investigation to see if these heuristics lead to models that are more interpretable to humans. In the era of data-driven learning, this is an important research direction to pursue. This paper describes our work-in-progress towards developing an AL selection function that in addition to model effectiveness also seeks to improve on the interpretability of a model during the bootstrapping steps. Concretely speaking, our proposed selection function trains an ’explainer’ model in addition to the classifier model, and favours those instances where a different part of the data is used, on an average, to explain the predicted class. Initial experiments exhibited encouraging trends in showing that such a heuristic can lead to developing more effective and more explainable end-to-end data-driven classifiers.

The video of this talk cannot be embedded. You can watch it here:
https://dl.acm.org/doi/10.1145/3340531.3417456#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
 11:27 
 0
 0
 0
 0
 10:39 
 0
 0
 0
 0
 4:15 
 0
 0
 0
 0
 15:03 
 0
 0
 0
 0
 5:34 
 0
 0
 0
 0
 7:26 
 0
 0
 0
 0
 13:49 
 0
 0
 0
 0
 5:17 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 2:56 
 0
 0
 0
 0
 2:42 
 0
 0
 0
 0
 3:12 
 1
 0
 0
 0
 5:06 
 0
 0
 0
 1
 5:13 
 0
 0
 0
 0
 13:54 
 0
 0
 0
 0
 16:45 
 0
 0
 0
 0
 17:04 
 0
 0
 0
 0
 15:28 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 3:06 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 10:54 
 0
 0
 0
 0
 2:28 
 1
 0
 0
 0
 5:08 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 2:22 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 15:12 
 0
 0
 0
 0
 9:52 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 15:08 
 0
 0
 0
 0
 3:31 
 0
 0
 0
 0
 15:28 
 0
 0
 0
 0
 14:31 
 0
 0
 0
 0
 3:16 
 0
 0
 0
 0
 15:01