SCOPE-FE reduces candidate feature generation time in automatic feature engineering by pre-pruning operators and limiting combinations to clustered feature groups while preserving predictive performance on benchmarks.
Learning a data-driven policy network for pre- training automated feature engineering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SCOPE-FE: Structured Control of Operator and Pairwise Exploration for Feature Engineering
SCOPE-FE reduces candidate feature generation time in automatic feature engineering by pre-pruning operators and limiting combinations to clustered feature groups while preserving predictive performance on benchmarks.