Distributed and Deep Vertical Federated Learning with Big Data

TL;DR

This paper introduces a distributed vertical federated learning framework that enhances training efficiency and data security using homomorphic encryption, demonstrating significant scalability and speed improvements in large-scale environments.

Contribution

It proposes a novel distributed vertical federated learning approach combining distributed architecture with homomorphic encryption for improved efficiency and security.

Findings

Achieves up to 6.8x faster training with a single server.

Achieves up to 15.1x faster training with multiple servers.

Demonstrates good scalability and efficiency in large-scale experiments.

Abstract

In recent years, data are typically distributed in multiple organizations while the data security is becoming increasingly important. Federated Learning (FL), which enables multiple parties to collaboratively train a model without exchanging the raw data, has attracted more and more attention. Based on the distribution of data, FL can be realized in three scenarios, i.e., horizontal, vertical, and hybrid. In this paper, we propose to combine distributed machine learning techniques with Vertical FL and propose a Distributed Vertical Federated Learning (DVFL) approach. The DVFL approach exploits a fully distributed architecture within each party in order to accelerate the training process. In addition, we exploit Homomorphic Encryption (HE) to protect the data against honest-but-curious participants. We conduct extensive experimentation in a large-scale cluster environment and a cloud environment in order to show the efficiency and scalability of our proposed approach. The experiments demonstrate the good scalability of our approach and the significant efficiency advantage (up to 6.8 times with a single server and 15.1 times with multiple servers in terms of the training time) compared with baseline frameworks.