Interpret Federated Learning with Shapley Values

Abstract

Federated Learning is introduced to protect privacy by distributing training data into multiple parties. Each party trains its own model and a meta-model is constructed from the sub models. In this way the details of the data are not disclosed in between each party. In this paper we investigate the model interpretation methods for Federated Learning, specifically on the measurement of feature importance of vertical Federated Learning where feature space of the data is divided into two parties, namely host and guest. For host party to interpret a single prediction of vertical Federated Learning model, the interpretation results, namely the feature importance, are very likely to reveal the protected data from guest party. We propose a method to balance the model interpretability and data privacy in vertical Federated Learning by using Shapley values to reveal detailed feature importance for host features and a unified importance value for federated guest features. Our experiments indicate robust and informative results for interpreting Federated Learning models.

References in corpus (5)

• Scikit-learn: Machine Learning in Python
• Learning Important Features Through Propagating Activation Differences
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Distilling a Neural Network Into a Soft Decision Tree

Cited by in corpus (7)

• From Distributed Machine Learning to Federated Learning: A Survey
• Federated Learning for Healthcare Informatics
• Asynchronous Federated Learning with Differential Privacy for Edge Intelligence
• A VCG-based Fair Incentive Mechanism for Federated Learning
• Applications of Federated Learning in Smart Cities: Recent Advances, Taxonomy, and Open Challenges
• IFedAvg: Interpretable Data-Interoperability for Federated Learning
• Optimal Procurement Auction for Cooperative Production of Virtual Products: Vickrey-Clarke-Groves Meet Cremer-McLean