Towards the Automated Composition of Machine Learning Services
Abstract
Automated service composition as the process of creating new software in an automated fashion has been studied in many different ways over the last decade. However, the impact of automated service composition has been rather small as its utility in real-world applications has not been demonstrated so far. This paper describes the use case of automated machine learning, a real-world scenario in which automated service composition plays an important role. It turns out that most existing service composition approaches are not able to reasonably solve this problem, because it requires to evaluate candidates by executing them during search. We briefly sketch a new service composition algorithm, MLS-PLAN, and illustrate how it can be applied to the problem of automated machine learning.
Details
- External Organisation(s)
-
Paderborn University
- Type
- Conference contribution
- Pages
- 241-244
- No. of pages
- 4
- Publication date
- 2018
- Publication status
- Published
- Peer reviewed
- Yes
- ASJC Scopus subject areas
- Information Systems and Management, Hardware and Architecture, Computer Networks and Communications, Computer Science Applications
- Electronic version(s)
-
https://doi.org/10.1109/SCC.2018.00039 (Access:
Closed
)
