Vertical Federated Learning in Practice: The Good, the Bad, and the Ugly

TL;DR

This paper surveys the practical deployment challenges of Vertical Federated Learning, analyzing real-world data distributions, identifying gaps in current research, and proposing directions to improve real-world applicability.

Contribution

It introduces a data-oriented taxonomy of VFL algorithms based on real data distributions and highlights the disconnect between current research and practical deployment.

Findings

Real-world data distributions often differ from assumptions in existing VFL algorithms.

Many practical VFL scenarios lack effective solutions.

The paper outlines research directions to bridge the gap between theory and practice.

Abstract

Vertical Federated Learning (VFL) is a privacy-preserving collaborative learning paradigm that enables multiple parties with distinct feature sets to jointly train machine learning models without sharing their raw data. Despite its potential to facilitate cross-organizational collaborations, the deployment of VFL systems in real-world applications remains limited. To investigate the gap between existing VFL research and practical deployment, this survey analyzes the real-world data distributions in potential VFL applications and identifies four key findings that highlight this gap. We propose a novel data-oriented taxonomy of VFL algorithms based on real VFL data distributions. Our comprehensive review of existing VFL algorithms reveals that some common practical VFL scenarios have few or no viable solutions. Based on these observations, we outline key research directions aimed at bridging the gap between current VFL research and real-world applications.