VFL-RPS: Relevant Participant Selection in Vertical Federated Learning

TL;DR

This paper introduces VFL-RPS, a novel participant selection method for vertical federated learning, improving model performance by selecting key participants and outperforming existing methods.

Contribution

The paper proposes VFL-RPS, a new participant selection approach specifically designed for vertical federated learning, addressing a gap in existing research focused mainly on horizontal FL.

Findings

VFL-RPS achieves comparable results to using all data with fewer participants.

VFL-RPS outperforms existing participant selection methods in VFL.

The method is effective for both regression and classification tasks.

Abstract

Federated Learning (FL) allows collaboration between different parties, while ensuring that the data across these parties is not shared. However, not every collaboration is helpful in terms of the resulting model performance. Therefore, it is an important challenge to select the correct participants in a collaboration. As it currently stands, most of the efforts in participant selection in the literature have focused on Horizontal Federated Learning (HFL), which assumes that all features are the same across all participants, disregarding the possibility of different features across participants which is captured in Vertical Federated Learning (VFL). To close this gap in the literature, we propose a novel method VFL-RPS for participant selection in VFL, as a pre-training step. We have tested our method on several data sets performing both regression and classification tasks, showing that our method leads to comparable results as using all data by only selecting a few participants. In addition, we show that our method outperforms existing methods for participant selection in VFL.