Secure Federated Transfer Learning

Abstract

Machine learning relies on the availability of a vast amount of data for training. However, in reality, most data are scattered across different organizations and cannot be easily integrated under many legal and practical constraints. In this paper, we introduce a new technique and framework, known as federated transfer learning (FTL), to improve statistical models under a data federation. The federation allows knowledge to be shared without compromising user privacy, and enables complimentary knowledge to be transferred in the network. As a result, a target-domain party can build more flexible and powerful models by leveraging rich labels from a source-domain party. A secure transfer cross validation approach is also proposed to guard the FTL performance under the federation. The framework requires minimal modifications to the existing model structure and provides the same level of accuracy as the non-privacy-preserving approach. This framework is very flexible and can be effectively adapted to various secure multi-party machine learning tasks.

IEEE Intelligent Systems, doi: 10.1109/MIS.2020.2988525

References in corpus (2)

• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• Entity Resolution and Federated Learning get a Federated Resolution

Cited by in corpus (85)

• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study
• Vertical Federated Learning: Concepts, Advances and Challenges
• FedML: A Research Library and Benchmark for Federated Machine Learning
• SecureBoost: A Lossless Federated Learning Framework
• Decentralized Federated Learning: A Survey on Security and Privacy
• Federated Adversarial Domain Adaptation
• Federated Forest
• Edge Intelligence: Architectures, Challenges, and Applications
• Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey
• Privacy-preserving Artificial Intelligence Techniques in Biomedicine
• Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning
• Federated learning: Applications, challenges and future directions
• Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
• PrivFL: Practical Privacy-preserving Federated Regressions on High-dimensional Data over Mobile Networks
• Privacy-Preserving Brain-Computer Interfaces: A Systematic Review
• Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning
• Federated Learning on Non-IID Data Silos: An Experimental Study
• Federated Multi-view Matrix Factorization for Personalized Recommendations
• FedCVT: Semi-supervised Vertical Federated Learning with Cross-view Training
• A Communication Efficient Collaborative Learning Framework for Distributed Features
• Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospective
• Private Federated Learning with Domain Adaptation
• Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations
• Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating
• The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
• FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning
• PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments
• Federated User Representation Learning
• Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
• Secure Shapley Value for Cross-Silo Federated Learning (Technical Report)
• FedVision: An Online Visual Object Detection Platform Powered by Federated Learning
• A Survey on Federated Learning and its Applications for Accelerating Industrial Internet of Things
• Practical Federated Gradient Boosting Decision Trees
• A Privacy Preserving System for Movie Recommendations Using Federated Learning
• Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks
• Quantifying the Performance of Federated Transfer Learning
• Federated Neural Architecture Search
• The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost
• A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
• Hybrid Differentially Private Federated Learning on Vertically Partitioned Data
• Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms
• Self-supervised Cross-silo Federated Neural Architecture Search
• FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning
• Continual Horizontal Federated Learning for Heterogeneous Data
• Federated Uncertainty-Aware Learning for Distributed Hospital EHR Data
• A Privacy-Preserving Federated Framework with Hybrid Quantum-Enhanced Learning for Financial Fraud Detection
• Residue-based Label Protection Mechanisms in Vertical Logistic Regression
• Turn Signal Prediction: A Federated Learning Case Study
• A Comprehensive Analysis of Information Leakage in Deep Transfer Learning
• Layer-wise Characterization of Latent Information Leakage in Federated Learning
• FedGL: Federated Graph Learning Framework with Global Self-Supervision
• Federated learning in food research
• From Federated Learning to Federated Neural Architecture Search: A Survey
• Federated Learning System without Model Sharing through Integration of Dimensional Reduced Data Representations
• Federated Learning -- Methods, Applications and beyond
• Combining Federated Learning and Control: A Survey
• Aggregate or Not? Exploring Where to Privatize in DNN Based Federated Learning Under Different Non-IID Scenes
• Federated Learning on Non-IID Data: A Survey
• RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation
• Differential Privacy-Driven Framework for Enhancing Heart Disease Prediction
• FedST: Secure Federated Shapelet Transformation for Time Series Classification
• Personalised Federated Learning On Heterogeneous Feature Spaces
• Addressing Class Imbalance in Federated Learning
• Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
• Federated Loss Exploration for Improved Convergence on Non-IID Data
• Federated Multi-Target Domain Adaptation
• Federated Generative Adversarial Learning
• Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection
• Federated Crowdsensing: Framework and Challenges
• Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX
• Distributed Machine Learning for Wireless Communication Networks: Techniques, Architectures, and Applications
• Personalized Federated Learning over non-IID Data for Indoor Localization
• Enabling SQL-based Training Data Debugging for Federated Learning
• Federated Extra-Trees with Privacy Preserving
• VerifyTL: Secure and Verifiable Collaborative Transfer Learning
• Pocket Diagnosis: Secure Federated Learning against Poisoning Attack in the Cloud
• Fed-EINI: An Efficient and Interpretable Inference Framework for Decision Tree Ensembles in Federated Learning
• Matrix Sketching for Secure Collaborative Machine Learning
• Privacy-Preserving Self-Taught Federated Learning for Heterogeneous Data
• Communication Efficient Federated Learning with Adaptive Quantization
• Knowledge Federation: A Unified and Hierarchical Privacy-Preserving AI Framework
• Management of Resource at the Network Edge for Federated Learning
• Multi-Party Dual Learning