1 Department of Computer Science and Engineering, HKUST
2 Laboratory for Information & Decision Systems, MIT
3 College of Computer Science and Technology, Zhejiang University
To relieve the pain of manually selecting machine learning algorithms and tuning hyperparameters, automated machine learning (AutoML) methods have been developed to automatically search for good models. Due to the huge model search space, it is impossible to try all models. Users tend to distrust automatic results and increase the search budget as much as they can, thereby undermining the efficiency of AutoML. To address these issues, we design and implement ATMSeer, an interactive visualization tool that supports users in refining the search space of AutoML and analyzing the results. To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts. A multi-granularity visualization is proposed to enable users to monitor the AutoML process, analyze the searched models, and refine the search space in real time. We demonstrate the utility and usability of ATMSeer through two case studies, expert interviews, and a user study with 13 end users.
The user creates/resume AutoML process using the control panel (a),
observe the high-level statistics of an AutoML process in the overview panel (b),
and analyze the process in different granularities with the AutoML profiler (c).
@InProceedings{wang2018atmseer,
title={ATMSeer: Increasing Transparency and Controllability in Automated Machine Learnings},
author={Wang, Qianwen and Ming, Yao and Jin, Zhihua and Shen, Qiaomu and Liu, Dongyu and Smith, Micah J. and Veeramachaneni, Kalyan, and Qu, Huamin},
booktitle = {Conference on Human Factors in Computing Systems (CHI)},
year = {2018}
}