Pith. sign in

org/10.1007/978-3-031-63797-1_22

URL http://dx · Communications in computer and information science · DOI 10.1007/978-3-031-63797-1_22

1 Pith paper cite this work, alongside 31 external citations. Polarity classification is still indexing.

1 Pith paper citing it
31 external citations · OpenAlex
open at publisher browse 1 citing papers

fields

stat.ML 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Aggregate Models, Not Explanations: Improving Feature Importance Estimation

stat.ML · 2026-02-12 · conditional · novelty 6.0

For risk-based feature importance (LOCO, SAGE), computing importance on an ensemble of models is more accurate than averaging individual models' importance scores, because model-level ensembling reduces the excess risk that dominates importance error.

citing papers explorer

Showing 1 of 1 citing paper.

  • Aggregate Models, Not Explanations: Improving Feature Importance Estimation stat.ML · 2026-02-12 · conditional · none · ref 22

    For risk-based feature importance (LOCO, SAGE), computing importance on an ensemble of models is more accurate than averaging individual models' importance scores, because model-level ensembling reduces the excess risk that dominates importance error.