EUVIMEDEUVIMED entdecken
Crossref

XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learning

Marc-André Zöller, Waldemar Titov, Thomas Schlegel, Marco F. Huber

ACM Transactions on Interactive Intelligent Systems · 31.12.2023 · 13 (4) · 1-39

DOI: 10.1145/3625240 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Interactive Intelligent Systems, online erschienen am 08.12.2023. Verfasst von Marc-André Zöller und 3 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 90 Literaturangaben. Gefördert von: German Federal Ministry for Economic Affairs and Climate Action in the project FabOS, German Federal Ministry of Education and Research, Baden-Wuerttemberg Ministry for Economic Affairs, Labour and Tourism.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the last 10 years, various automated machine learning (AutoML) systems have been proposed to build end-to-end machine learning (ML) pipelines with minimal human interaction. Even though such automatically synthesized ML pipelines are able to achieve competitive performance, recent studies have shown that users do not trust models constructed by AutoML due to missing transparency of AutoML systems and missing explanations for the constructed ML pipelines. In a requirements analysis study with 36 domain experts, data scientists, and AutoML researchers from different professions with vastly different expertise in ML, we collect detailed informational needs for AutoML. We propose XAutoML , an interactive visual analytics tool for explaining arbitrary AutoML optimization procedures and ML pipelines constructed by AutoML. XAutoML combines interactive visualizations with established techniques from explainable artificial intelligence (XAI) to make the complete AutoML procedure transparent and explainable. By integrating XAutoML with JupyterLab , experienced users can extend the visual analytics with ad-hoc visualizations based on information extracted from XAutoML . We validate our approach in a user study with the same diverse user group from the requirements analysis. All participants were able to extract useful information from XAutoML , leading to a significantly increased understanding of ML pipelines produced by AutoML and the AutoML optimization itself.

Förderung

  • German Federal Ministry for Economic Affairs and Climate Action in the project FabOS
  • German Federal Ministry of Education and Research
  • Baden-Wuerttemberg Ministry for Economic Affairs, Labour and Tourism
  • Lernende Systeme und Kognitive Robotik

Zitieren

APA

Zöller, M., Titov, W., Schlegel, T., & Huber, M. F. (2023). XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learning. ACM Transactions on Interactive Intelligent Systems, 13(4), 1-39. https://doi.org/10.1145/3625240

Vancouver

Zöller M, Titov W, Schlegel T, Huber MF. XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learning. ACM Transactions on Interactive Intelligent Systems. 2023;13(4):1-39. doi:10.1145/3625240

BibTeX
@article{Zller2023,
  author = {Zöller, Marc-André and Titov, Waldemar and Schlegel, Thomas and Huber, Marco F.},
  title = {XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learning},
  journal = {ACM Transactions on Interactive Intelligent Systems},
  year = {2023},
  volume = {13},
  number = {4},
  pages = {1--39},
  doi = {10.1145/3625240}
}
Kostenlos starten →