PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN
Machine Learning
2021-04-15 v3 Cryptography and Security
Distributed, Parallel, and Cluster Computing
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.
Keywords
Cite
@article{arxiv.2104.00489,
title = {PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN},
author = {Daniele Romanini and Adam James Hall and Pavlos Papadopoulos and Tom Titcombe and Abbas Ismail and Tudor Cebere and Robert Sandmann and Robin Roehm and Michael A. Hoeh},
journal= {arXiv preprint arXiv:2104.00489},
year = {2021}
}
Comments
ICLR 2021 Workshop on Distributed and Private Machine Learning (DPML 2021)