TY - GEN
T1 - AutoAIViz
T2 - 25th ACM International Conference on Intelligent User Interfaces, IUI 2020
AU - Weidele, Daniel Karl I.
AU - Weisz, Justin D.
AU - Oduor, Erick
AU - Muller, Michael
AU - Andres, Josh
AU - Gray, Alexander
AU - Wang, Dakuo
N1 - Publisher Copyright:
© ACM.
PY - 2020/3/17
Y1 - 2020/3/17
N2 - Artificial Intelligence (AI) can now automate the algorithm selection, feature engineering, and hyperparameter tuning steps in a machine learning workflow. Commonly known as AutoML or AutoAI, these technologies aim to relieve data scientists from the tedious manual work. However, today's AutoAI systems often present only limited to no information about the process of how they select and generate model results. Thus, users often do not understand the process, neither do they trust the outputs. In this short paper, we provide a first user evaluation by 10 data scientists of an experimental system, AutoAIViz, that aims to visualize AutoAI's model generation process. We find that the proposed system helps users to complete the data science tasks, and increases their understanding, toward the goal of increasing trust in the AutoAI system.
AB - Artificial Intelligence (AI) can now automate the algorithm selection, feature engineering, and hyperparameter tuning steps in a machine learning workflow. Commonly known as AutoML or AutoAI, these technologies aim to relieve data scientists from the tedious manual work. However, today's AutoAI systems often present only limited to no information about the process of how they select and generate model results. Thus, users often do not understand the process, neither do they trust the outputs. In this short paper, we provide a first user evaluation by 10 data scientists of an experimental system, AutoAIViz, that aims to visualize AutoAI's model generation process. We find that the proposed system helps users to complete the data science tasks, and increases their understanding, toward the goal of increasing trust in the AutoAI system.
KW - AutoAI
KW - AutoML
KW - democratizing AI
KW - human-AI collaboration
KW - parallel coordinates
KW - visualization
UR - http://www.scopus.com/inward/record.url?scp=85082456533&partnerID=8YFLogxK
U2 - 10.1145/3377325.3377538
DO - 10.1145/3377325.3377538
M3 - Conference contribution
T3 - International Conference on Intelligent User Interfaces, Proceedings IUI
SP - 308
EP - 312
BT - Proceedings of the 25th International Conference on Intelligent User Interfaces, IUI 2020
PB - Association for Computing Machinery (ACM)
Y2 - 17 March 2020 through 20 March 2020
ER -