TY - GEN
T1 - A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations
AU - Krause, Josua
AU - Dasgupta, Aritra
AU - Swartz, Jordan
AU - Aphinyanaphongs, Yindalon
AU - Bertini, Enrico
N1 - Funding Information:
We thank Prof. Foster Provost for his help in understanding and using his instance-level explanation technique. The research described in this paper is part of the Analysis in Motion Initiative at Pacific Northwest National Laboratory (PNNL). It was conducted under the Laboratory Directed Research and Development Program at PNNL, a multi-program national laboratory operated by Battelle. Battelle operates PNNL for the U.S. Department of Energy (DOE) under contract DE-AC05-76RLO01830. The work has also been partially funded by the Google Faculty Research Award ”Interactive Visual Explanation of Classification Models”.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and domain experts explore, diagnose, and understand the decisions made by a binary classifier. The approach leverages 'instance-level explanations', measures of local feature relevance that explain single instances, and uses them to build a set of visual representations that guide the users in their investigation. The workflow is based on three main visual representations and steps: one based on aggregate statistics to see how data distributes across correct / incorrect decisions; one based on explanations to understand which features are used to make these decisions; and one based on raw data, to derive insights on potential root causes for the observed patterns. The workflow is derived from a long-term collaboration with a group of machine learning and healthcare professionals who used our method to make sense of machine learning models they developed. The case study from this collaboration demonstrates that the proposed workflow helps experts derive useful knowledge about the model and the phenomena it describes, thus experts can generate useful hypotheses on how a model can be improved.
AB - Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and domain experts explore, diagnose, and understand the decisions made by a binary classifier. The approach leverages 'instance-level explanations', measures of local feature relevance that explain single instances, and uses them to build a set of visual representations that guide the users in their investigation. The workflow is based on three main visual representations and steps: one based on aggregate statistics to see how data distributes across correct / incorrect decisions; one based on explanations to understand which features are used to make these decisions; and one based on raw data, to derive insights on potential root causes for the observed patterns. The workflow is derived from a long-term collaboration with a group of machine learning and healthcare professionals who used our method to make sense of machine learning models they developed. The case study from this collaboration demonstrates that the proposed workflow helps experts derive useful knowledge about the model and the phenomena it describes, thus experts can generate useful hypotheses on how a model can be improved.
KW - Interpretation
KW - Machine Learning
KW - Visual Analytics
UR - http://www.scopus.com/inward/record.url?scp=85061067028&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061067028&partnerID=8YFLogxK
U2 - 10.1109/VAST.2017.8585720
DO - 10.1109/VAST.2017.8585720
M3 - Conference contribution
AN - SCOPUS:85061067028
T3 - 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings
SP - 162
EP - 172
BT - 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings
A2 - Schreck, Tobias
A2 - Fisher, Brian
A2 - Liu, Shixia
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017
Y2 - 1 October 2017 through 6 October 2017
ER -