@inproceedings{9a67cc1e38214e6a85c28dfe074f5099,
title = "A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations",
abstract = "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.",
keywords = "Interpretation, Machine Learning, Visual Analytics",
author = "Josua Krause and Aritra Dasgupta and Jordan Swartz and Yindalon Aphinyanaphongs and Enrico Bertini",
note = "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: {\textcopyright} 2017 IEEE.; 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 ; Conference date: 01-10-2017 Through 06-10-2017",
year = "2018",
month = dec,
day = "21",
doi = "10.1109/VAST.2017.8585720",
language = "English (US)",
series = "2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "162--172",
editor = "Tobias Schreck and Brian Fisher and Shixia Liu",
booktitle = "2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings",
address = "United States",
}