PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN
This addresses privacy-preserving machine learning for data owners in federated settings, but it is incremental as it builds on existing split neural network and vertical federated learning concepts.
The authors tackled the problem of training neural networks on vertically partitioned data across multiple owners without sharing raw data, and demonstrated the framework's validity by achieving classification on MNIST with data distributed across two owners and a scientist.
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.