Online AutoML: an adaptive AutoML framework for online learning

Bilge Celik (Corresponding author), Prabhant Singh (Corresponding author), Joaquin Vanschoren (Corresponding author)

Research output: Contribution to journalArticleAcademicpeer-review

7 Citations (Scopus)
21 Downloads (Pure)

Abstract

Automated Machine Learning (AutoML) has been used successfully in settings where the learning task is assumed to be static. In many real-world scenarios, however, the data distribution will evolve over time, and it is yet to be shown whether AutoML techniques can effectively design online pipelines in dynamic environments. This study aims to automate pipeline design for online learning while continuously adapting to data drift. For this purpose, we design an adaptive Online Automated Machine Learning (OAML) system, searching the complete pipeline configuration space of online learners, including preprocessing algorithms and ensembling techniques. This system combines the inherent adaptation capabilities of online learners with fast automated pipeline (re)optimization. Focusing on optimization techniques that can adapt to evolving objectives, we evaluate asynchronous genetic programming and asynchronous successive halving to optimize these pipelines continually. We experiment on real and artificial data streams with varying types of concept drift to test the performance and adaptation capabilities of the proposed system. The results confirm the utility of OAML over popular online learning algorithms and underscore the benefits of continuous pipeline redesign in the presence of data drift.

Original languageEnglish
Pages (from-to)1897-1921
Number of pages25
JournalMachine Learning
Volume112
Issue number6
Early online date6 Dec 2022
DOIs
Publication statusPublished - Jun 2023

Bibliographical note

Funding Information:
The research is funded under the NWO project DACCOMPLI and partially by TAILOR project.

Funding Information:
We would like to give special thanks to Pieter Gijsbers for his help in integrating OAML into the GAMA library. This research was supported by the Dutch Foundation for Scientific Research (NWO) under the DACCOMPLI grant, and by the European Commission’s H2020 program under the StairwAI grant. It was also partially supported by TAILOR, a project funded by EU Horizon 2020 research and innovation programme under GA No 952215.

Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature.

Keywords

  • Automated drift adaptation
  • Automated online learning
  • Concept drift
  • Online automl

Fingerprint

Dive into the research topics of 'Online AutoML: an adaptive AutoML framework for online learning'. Together they form a unique fingerprint.

Cite this