Retrain AI Systems Responsibly! Use Sustainable Concept Drift Adaptation Techniques
Lorena Poenaru-Olaru (TU Delft - Electrical Engineering, Mathematics and Computer Science)
June Sallou (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Luis Cruz (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Jan S. Rellermeyer (Leibniz Universität, TU Delft - Electrical Engineering, Mathematics and Computer Science)
Arie Van Deursen (TU Delft - Electrical Engineering, Mathematics and Computer Science)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
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.