Testing the Robustness of AutoML Systems

Tuomas Halvari
Jukka K. Nurminen
Tommi Mikkonen

Automated machine learning (AutoML) systems aim at finding the best machine learning (ML) pipeline that automatically matches the task and data at hand. We investigate the robustness of machine learning pipelines generated with three AutoML systems, TPOT, H2O, and AutoKeras. In particular, we study the influence of dirty data on accuracy, and consider how using dirty training data may help create more robust solutions. Furthermore, we also analyze how the structure of the generated pipelines differs in different cases.

In Rafael C. Cardoso, Angelo Ferrando, Daniela Briola, Claudio Menghi and Tobias Ahlbrecht: Proceedings of the First Workshop on Agents and Robots for reliable Engineered Autonomy (AREA 2020), Virtual event, 4th September 2020, Electronic Proceedings in Theoretical Computer Science 319, pp. 103–116.
Published: 23rd July 2020.

ArXived at: http://dx.doi.org/10.4204/EPTCS.319.8 bibtex PDF
References in reconstructed bibtex, XML and HTML format (approximated).
Comments and questions to: eptcs@eptcs.org
For website issues: webmaster@eptcs.org