Secure Logistic Regression for Vertical Federated Learning

Data island effectively blocks the practical application of machine learning. To meet this challenge, a new framework known as federated learning was created. It allows model training on large amount scattered data owned by different providers. This article presents parallel solution for computing logistic regression based distributed asynchronous task framework. Compared to existing work, our proposed does not rely any third-party coordinator, and hence has better security can solve multitraining problem. The homomorphic encryption is implemented in Python, which used vertical prediction resulting model. We evaluate using MNIST dataset, experimental results show that good performance achieved.