Vertical Federated Learning: Concepts, Advances and Challenges

Abstract

Vertical Federated Learning (VFL) is a federated learning setting where multiple parties with different features about the same set of users jointly train machine learning models without exposing their raw data or model parameters. Motivated by the rapid growth in VFL research and real-world applications, we provide a comprehensive review of the concept and algorithms of VFL, as well as current advances and challenges in various aspects, including effectiveness, efficiency, and privacy. We provide an exhaustive categorization for VFL settings and privacy-preserving protocols and comprehensively analyze the privacy attacks and defense strategies for each protocol. In the end, we propose a unified framework, termed VFLow, which considers the VFL problem under communication, computation, privacy, as well as effectiveness and fairness constraints. Finally, we review the most recent advances in industrial applications, highlighting open challenges and future directions for VFL.

We added new works and revised the manuscript

References in corpus (22)

• Explaining and Harnessing Adversarial Examples
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• Privacy Preserving Vertical Federated Learning for Tree-based Models
• Multi-Participant Multi-Class Vertical Federated Learning
• PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN
• Backdoor attacks and defenses in feature-partitioned collaborative learning
• Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates
• Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning
• A Vertical Federated Learning Framework for Graph Convolutional Network
• AsySQN: Faster Vertical Federated Learning Algorithms with Better Computation Resource Utilization
• Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks
• Hybrid Differentially Private Federated Learning on Vertically Partitioned Data
• Vertical Federated Learning without Revealing Intersection Membership
• A Vertical Federated Learning Method for Interpretable Scorecard and Its Application in Credit Scoring
• Efficient Batch Homomorphic Encryption for Vertically Federated XGBoost
• Label Leakage and Protection from Forward Embedding in Vertical Federated Learning
• Defending against Reconstruction Attack in Vertical Federated Learning
• FedGBF: An efficient vertical federated learning framework via gradient boosting and bagging
• Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning
• Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond
• Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learning
• Protecting Split Learning by Potential Energy Loss

Cited by in corpus (10)

• Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities
• Federated learning, ethics, and the double black box problem in medical AI
• Personalized Federated Continual Learning via Multi-granularity Prompt
• A Privacy-Preserving Federated Framework with Hybrid Quantum-Enhanced Learning for Financial Fraud Detection
• Federated learning in food research
• EASTER: Embedding Aggregation-based Heterogeneous Models Training in Vertical Federated Learning
• Privacy Preserving Conversion Modeling in Data Clean Room
• Sample-Independent Federated Learning Backdoor Attack in Speaker Recognition
• One-Shot Clustering for Federated Learning
• Stalactite: Toolbox for Fast Prototyping of Vertical Federated Learning Systems