Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey

TL;DR

This survey systematically reviews recent developments in Vertical Federated Learning, focusing on effectiveness, security, and applicability, to address scattered research and guide future advancements in the field.

Contribution

It provides a comprehensive, organized overview of VFL research, analyzing limitations and proposing future directions across key aspects.

Findings

VFL effectively enables privacy-preserving cross-domain collaboration.

Security challenges remain significant in VFL implementations.

Research in VFL is rapidly evolving with ongoing updates and community resources.

Abstract

Vertical Federated Learning (VFL) is a privacy-preserving distributed learning paradigm where different parties collaboratively learn models using partitioned features of shared samples, without leaking private data. Recent research has shown promising results addressing various challenges in VFL, highlighting its potential for practical applications in cross-domain collaboration. However, the corresponding research is scattered and lacks organization. To advance VFL research, this survey offers a systematic overview of recent developments. First, we provide a history and background introduction, along with a summary of the general training protocol of VFL. We then revisit the taxonomy in recent reviews and analyze limitations in-depth. For a comprehensive and structured discussion, we synthesize recent research from three fundamental perspectives: effectiveness, security, and applicability. Finally, we discuss several critical future research directions in VFL, which will facilitate the developments in this field. We provide a collection of research lists and periodically update them at https://github.com/shentt67/VFL_Survey.