Voting on Features: Federated Feature Selection Without Sharing Data

A method called Feature Election enables collaborative feature selection in federated learning environments without sharing raw data. Each participating site independently runs a local feature selector and sends a mask, preference scores, and its sample count to a central server. The server aggregates these votes, using a tunable "freedom degree" parameter to resolve disagreements on which features to keep. This process allows different entities to agree on a common feature set for a shared model while preserving the privacy of their local data.