Print Email Facebook Twitter Retrain AI Systems Responsibly! Use Sustainable Concept Drift Adaptation Techniques Title Retrain AI Systems Responsibly! Use Sustainable Concept Drift Adaptation Techniques Author Poenaru-Olaru, L. (TU Delft Software Engineering) Sallou, J. (TU Delft Software Engineering) Cruz, Luis (TU Delft Software Engineering) Rellermeyer, Jan S. (TU Delft Data-Intensive Systems; Leibniz Universität) van Deursen, A. (TU Delft Software Technology) Department Software Technology Date 2023 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. Subject concept drift adaptationsustainable model maintenancesustainable model retraining To reference this document use: http://resolver.tudelft.nl/uuid:d115c5ba-f671-4713-9513-a0c7c5abf7f1 DOI https://doi.org/10.1109/GREENS59328.2023.00009 Publisher IEEE Embargo date 2024-02-05 ISBN 9798350312386 Source Proceedings - 2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software, GREENS 2023 Event 7th IEEE/ACM International Workshop on Green And Sustainable Software, GREENS 2023, 2023-05-14 → , Melbourne, Australia Series Proceedings - 2023 IEEE/ACM 7th International Workshop on Green And Sustainable Software, GREENS 2023 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-care Otherwise 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. Part of collection Institutional Repository Document type conference paper Rights © 2023 L. Poenaru-Olaru, J. Sallou, Luis Cruz, Jan S. Rellermeyer, A. van Deursen Files PDF Retrain_AI_Systems_Respon ... niques.pdf 260.27 KB Close viewer /islandora/object/uuid:d115c5ba-f671-4713-9513-a0c7c5abf7f1/datastream/OBJ/view