25/04/2020

Interpreting Interpretability: Understanding Data Scientists’ Use of Interpretability Tools for Machine Learning

Harmanpreet Kaur, Harsha Nori, Samuel Jenkins, Rich Caruana, Hanna Wallach, Jennifer Wortman Vaughan

Keywords: interpretability, machine learning, user-centric evaluation

Abstract Paper Similar Papers

Abstract: Machine learning (ML) models are now routinely deployed in domains ranging from criminal justice to healthcare. With this newfound ubiquity, ML has moved beyond academia and grown into an engineering discipline. To that end, interpretability tools have been designed to help data scientists and machine learning practitioners better understand how ML models work. However, there has been little evaluation of the extent to which these tools achieve this goal. We study data scientists’ use of two existing interpretability tools, the InterpretML implementation of GAMs and the SHAP Python package. We conduct a contextual inquiry (N=11) and a survey (N=197) of data scientists to observe how they use interpretability tools to uncover common issues that arise when building and evaluating ML models. Our results indicate that data scientists over-trust and misuse interpretability tools. Furthermore, few of our participants were able to accurately describe the visualizations output by these tools. We highlight qualitative themes for data scientists’ mental models of interpretability tools. We conclude with implications for researchers and tool designers, and contextualize our findings in the social science literature.

The video of this talk cannot be embedded. You can watch it here:
https://www.youtube.com/watch?v=oMwF9CJGbwg
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at CHI 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
 15:29 
 0
 0
 0
 0
 17:26 
 0
 0
 0
 0
 9:27 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 4:14 
 0
 0
 0
 0
 11:24 
 0
 0
 0
 0
 9:41 
 0
 0
 0
 0
 14:25 
 0
 0
 0
 0
 6:16 
 0
 0
 0
 0
 15:42 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 14:08 
 0
 0
 0
 0
 14:51 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 11:30 
 0
 0
 0
 0
 8:53 
 0
 0
 0
 0
 4:25 
 0
 0
 0
 0
 2:28 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 4:27 
 0
 0
 0
 0
 9:33 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 13:37 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 11:26 
 0
 0
 0
 0
 5:39 
 0
 0
 0
 0
 12:32 
 0
 0
 0
 0
 20:36 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 6:01 
 0
 0
 0
 0
 12:01 
 0
 0
 0
 0
 10:26 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 12:53 
 0
 0
 0
 0
 19:10