AutoML: Towards automation of machine learning systems maintainability

Lorena Poenaru-Olaru*

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

43 Downloads (Pure)

Abstract

Machine learning systems both gained significant interest from the academic side and have seen adoption in the industry. However, one aspect that has received insufficient attention so far is the study of the lifecycle of such systems. This aspect is particularly important due to various ML systems' strong dependency on data, which is constantly evolving-and, therefore, changing-over time. The focus of my PhD research is the study of the implications of these dynamics on the ML systems' performance. Concretely, I propose a method of detecting changes caused by drift in the data early. Furthermore, I discuss possibilities for automating large parts of the ML lifecycle management, to ensure a better and more controllable maintenance process.

Original languageEnglish
Title of host publicationMiddleware 2021 Doctoral Symposium - Proceedings of the 22nd International Middleware Conference
Subtitle of host publicationDoctoral Symposium
PublisherAssociation for Computing Machinery (ACM)
Pages4-5
Number of pages2
ISBN (Electronic)9781450391559
DOIs
Publication statusPublished - 2021
Event22nd International Middleware Conference, Middleware 2021 - Virtual, Online, Canada
Duration: 6 Dec 202110 Dec 2021

Publication series

NameMiddleware 2021 Doctoral Symposium - Proceedings of the 22nd International Middleware Conference: Doctoral Symposium

Conference

Conference22nd International Middleware Conference, Middleware 2021
Country/TerritoryCanada
CityVirtual, Online
Period6/12/2110/12/21

Keywords

  • AutoML
  • concept drift detection
  • data shift

Fingerprint

Dive into the research topics of 'AutoML: Towards automation of machine learning systems maintainability'. Together they form a unique fingerprint.

Cite this