Retrain AI Systems Responsibly! Use Sustainable Concept Drift Adaptation Techniques

authored by

Lorena Poenaru-Olaru, June Sallou, Luis Miranda da Cruz, Jan S. Rellermeyer, Arie van Deursen

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.

Organisation(s)

Institute of Systems Engineering
Dependable and Scalable Software Systems

External Organisation(s)

Delft University of Technology

Type

Conference contribution

Pages

17-18

No. of pages

2

Publication date

2023

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

Software, Renewable Energy, Sustainability and the Environment

Sustainable Development Goals

SDG 7 - Affordable and Clean Energy

Electronic version(s)

https://doi.org/10.1109/greens59328.2023.00009 (Access: Closed)
http://resolver.tudelft.nl/uuid:d115c5ba-f671-4713-9513-a0c7c5abf7f1 (Access: Open)