How to Sustainably Monitor ML-Enabled Systems? Accuracy and Energy Efficiency Tradeoffs in Concept Drift Detection

arXiv:2404.19452v1 Announce Type: new
Abstract: ML-enabled systems that are deployed in a production environment typically suffer from decaying model prediction quality through concept drift, i.e., a gradual change in the statistical characteristics of a certain real-world domain. To combat this, a simple solution is to periodically retrain ML models, which unfortunately can consume a lot of energy. One recommended tactic to improve energy efficiency is therefore to systematically monitor the level of concept drift and only retrain when it becomes …

abstract accuracy arxiv change combat concept cs.lg cs.se detection domain drift efficiency energy energy efficiency environment prediction production quality simple solution statistical systems through type world