Ensemble methods improve recommender accuracy by 0.3-5.7% but raise energy use by 19-2549%, with selective strategies being more efficient than full averaging.
Assembled-openml: Creating efficient bench- marks for ensembles in AutoML with OpenML,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Ensembles at Any Cost? Accuracy-Energy Trade-offs in Recommender Systems
Ensemble methods improve recommender accuracy by 0.3-5.7% but raise energy use by 19-2549%, with selective strategies being more efficient than full averaging.