Retraining failure prediction models on recent data only, and only when drift detectors signal a change, reduces energy consumption while mostly preserving accuracy, but no single retraining strategy is best across all datasets.
Towards a consistent interpretation of aiops models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Sustainable Machine Learning Retraining: Optimizing Energy Efficiency Without Compromising Accuracy
Retraining failure prediction models on recent data only, and only when drift detectors signal a change, reduces energy consumption while mostly preserving accuracy, but no single retraining strategy is best across all datasets.