Multi-Participant Multi-Class Vertical Federated Learning

TL;DR

This paper introduces MMVFL, a novel multi-participant multi-class vertical federated learning framework that enables privacy-preserving label sharing among multiple parties, enhancing multi-class classification performance.

Contribution

It extends VFL to support multiple participants and classes, incorporating label sharing and feature selection, which were limited in prior two-party binary-focused studies.

Findings

MMVFL effectively shares label information among multiple VFL participants.

The framework achieves comparable multi-class classification accuracy to existing methods.

Incorporating feature selection improves model performance on real-world datasets.

Abstract

Federated learning (FL) is a privacy-preserving paradigm for training collective machine learning models with locally stored data from multiple participants. Vertical federated learning (VFL) deals with the case where participants sharing the same sample ID space but having different feature spaces, while label information is owned by one participant. Current studies of VFL only support two participants, and mostly focus on binaryclass logistic regression problems. In this paper, we propose the Multi-participant Multi-class Vertical Federated Learning (MMVFL) framework for multi-class VFL problems involving multiple parties. Extending the idea of multi-view learning (MVL), MMVFL enables label sharing from its owner to other VFL participants in a privacypreserving manner. To demonstrate the effectiveness of MMVFL, a feature selection scheme is incorporated into MMVFL to compare its performance against supervised feature selection and MVL-based approaches. Experiment results on real-world datasets show that MMVFL can effectively share label information among multiple VFL participants and match multi-class classification performance of existing approaches.