Can I read Balancing Interpretability and Privacy in Federated Learning on EtoBox?

Balancing Interpretability and Privacy in Federated Learning by Feng Yu is a document available to read on EtoBox.

What is Balancing Interpretability and Privacy in Federated Learning about?

This document discusses interpreting machine learning models trained with federated learning using Shapley values. Federated learning allows different parties to build a joint machine learning model without sharing private data. The document proposes using Shapley values to provide detailed feature importance for features owned by each party while providing a unified importance value for features from other parties, balancing model interpretability and privacy. This allows models trained with federated lear

Author

Feng Yu

Language

EN