Abstract
Deployed machine learning systems often suffer from accuracy degradation over time generated by constant data shifts, also known as concept drift. Therefore, these systems require regular maintenance, in which the machine learning model needs to be adapted to concept drift. The literature presents plenty of model adaptation techniques. The most common technique is periodically executing the whole training pipeline with all the data gathered until a particular point in time, yielding a massive energy footprint. In this paper, we propose a research path that uses concept drift detection and adaptation to enable sustainable AI systems.
Original language | English |
---|---|
Title of host publication | Proceedings - 2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software, GREENS 2023 |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 17-18 |
Number of pages | 2 |
ISBN (Electronic) | 9798350312386 |
DOIs | |
Publication status | Published - 2023 |
Event | 7th IEEE/ACM International Workshop on Green And Sustainable Software, GREENS 2023 - Melbourne, Australia Duration: 14 May 2023 → … |
Publication series
Name | Proceedings - 2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software, GREENS 2023 |
---|
Conference
Conference | 7th IEEE/ACM International Workshop on Green And Sustainable Software, GREENS 2023 |
---|---|
Country/Territory | Australia |
City | Melbourne |
Period | 14/05/23 → … |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Keywords
- concept drift adaptation
- sustainable model maintenance
- sustainable model retraining