Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning.
Jaehyun NamKyuyoung KimSeunghyuk OhJihoon TackJaehyung KimJinwoo ShinPublished in: CoRR (2024)
Keyphrases
- statistical analysis
- feature generation
- tabular data
- decision trees
- feature construction
- constructive induction
- inductive learning
- text categorization
- machine learning
- statistical approaches
- word sense disambiguation
- feature representations
- machine learning algorithms
- inductive logic programming
- statistical modeling
- generation method
- information extraction
- semantic features
- knowledge base
- genetic programming
- knowledge representation
- co training
- induction algorithms
- differential privacy
- classification rules
- knowledge discovery
- feature selection