Reproduce “CAFE: Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Arun Vignesh Malarkkan, Wangyang Ying, Yanjie Fu
CAFE uses learned causal structure to guide automated feature search for tabular prediction without excluding other features. It estimates a graph from training data, groups features by paths to the target, and uses reinforcement-learning agents to select transformations. On California-to-Texas employment, it retained 95.2% of its in-distribution F1. These observational results do not establish causal identification or guaranteed transportability.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.