A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations

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 - 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

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 - Fisher, Brian

A2 - Liu, Shixia

A2 - Schreck, Tobias

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 -