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.

arXiv commentWe added new works and revised the manuscript

References in corpus (48)

• Explaining and Harnessing Adversarial Examples
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Towards Personalized Federated Learning
• Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
• Secure Federated Transfer Learning
• Sparse Communication for Distributed Gradient Descent
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• FedML: A Research Library and Benchmark for Federated Machine Learning
• Automated Machine Learning: From Principles to Practices
• Feature Inference Attack on Model Predictions in Vertical Federated Learning
• Privacy Preserving Vertical Federated Learning for Tree-based Models
• Federated Transfer Learning for EEG Signal Classification
• Multi-Participant Multi-Class Vertical Federated Learning
• Label Leakage and Protection in Two-party Split Learning
• FedCVT: Semi-supervised Vertical Federated Learning with Cross-view Training
• PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN
• BlindFL: Vertical Federated Machine Learning without Peeking into Your Data
• Large-Scale Secure XGB for Vertical Federated Learning
• An Efficient Learning Framework For Federated XGBoost Using Secret Sharing And Distributed Optimization
• A Federated Learning Framework for Smart Grids: Securing Power Traces in Collaborative Learning
• FederBoost: Private Federated Learning for GBDT
• Backdoor attacks and defenses in feature-partitioned collaborative learning
• Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability
• Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates
• Asymmetrical Vertical Federated Learning
• 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
• SecureBoost+: Large Scale and High-Performance Vertical Federated Gradient Boosting Decision Tree
• Hybrid Differentially Private Federated Learning on Vertically Partitioned Data
• Federated Bandit: A Gossiping Approach
• FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning
• Vertical Federated Learning without Revealing Intersection Membership
• Feature-Distributed SVRG for High-Dimensional Linear Classification
• Fair and efficient contribution valuation for vertical federated learning
• Accelerating Vertical Federated Learning
• A Vertical Federated Learning Method for Interpretable Scorecard and Its Application in Credit Scoring
• Residue-based Label Protection Mechanisms in Vertical Logistic Regression
• Achieving Model Fairness in Vertical Federated Learning
• 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