PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN

2021/04/01 by Romanini, Daniele, Hall, Adam James, Papadopoulos, Pavlos +6 · 1 citation
#Cryptography and Security (cs.CR) #Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #and Cluster Computing (cs.DC)

paper · doi:10.48550/arxiv.2104.00489

Abstract

We introduce PyVertical, a framework supporting vertical federated learning using split neural networks. The proposed framework allows a data scientist to train neural networks on data features vertically partitioned across multiple owners while keeping raw data on an owner's device. To link entities shared across different datasets' partitions, we use Private Set Intersection on IDs associated with data points. To demonstrate the validity of the proposed framework, we present the training of a simple dual-headed split neural network for a MNIST classification task, with data samples vertically distributed across two data owners and a data scientist.

Cited by

• The Sherpa.ai Blind Vertical Federated Learning Paradigm to Minimize the Number of Communications

Related

• SplitNN-driven Vertical Partitioning
• A Vertical Federated Learning Framework for Horizontally Partitioned Labels
• Multi-VFL: A Vertical Federated Learning System for Multiple Data and Label Owners
• Spatio-Temporal Split Learning
• Vertical Federated Learning: A Structured Literature Review