Vertical federated learning based on DFP and BFGS

TL;DR

This paper introduces a novel vertical federated learning framework called BDFL, which leverages DFP and BFGS methods to improve communication efficiency and handle non-iid data, demonstrated through experiments on real datasets.

Contribution

The paper proposes a new vertical federated learning framework based on DFP and BFGS, addressing communication efficiency and non-iid data challenges in FL.

Findings

BDFL improves communication efficiency in federated learning.

The framework effectively handles non-iid data distributions.

Experimental results validate the framework's performance on real datasets.

Abstract

As data privacy is gradually valued by people, federated learning(FL) has emerged because of its potential to protect data. FL uses homomorphic encryption and differential privacy encryption on the promise of ensuring data security to realize distributed machine learning by exchanging encrypted information between different data providers. However, there are still many problems in FL, such as the communication efficiency between the client and the server and the data is non-iid. In order to solve the two problems mentioned above, we propose a novel vertical federated learning framework based on the DFP and the BFGS(denoted as BDFL), then apply it to logistic regression. Finally, we perform experiments using real datasets to test efficiency of BDFL framework.