A Secure Federated Transfer Learning Framework

Machine learning relies on the availability of vast amounts of data for training. However, in reality, data are mostly scattered across different organizations and cannot be easily integrated due to many legal and practical constraints. To address this important challenge in the field of machine learning, we introduce a new technique and framework, known as federated transfer learning (FTL), to improve statistical modeling under a data federation. FTL allows knowledge to be shared without compromising user privacy and enables complementary knowledge to be transferred across domains in a data federation, thereby enabling a target-domain party to build flexible and effective models by leveraging rich labels from a source domain. This framework requires minimal modifications to the existing model structure and provides the same level of accuracy as the nonprivacy-preserving transfer learning. It is flexible and can be effectively adapted to various secure multiparty machine learning tasks.

Authors

• Yang Liu College of Computer Science, Sichuan University Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education
• Yan Kang
• Chaoping Xing
• Tianjian Chen
• Qiang Yang Hong Kong University of Science and Technology, Hong Kong SAR, China

Keywords

• Encryption
• Neural networks
• Data models
• Collaborative work
• Training data
• Machine learning
• Adaption models
• Transfer Learning
• Federated Transfer Learning
• Secure Federated
• Federated Transfer Learning Framework
• Neural Network
• Federation
• Machine Learning Models
• Feature Space
• Small Datasets
• General Data Protection Regulation
• Source Domain
• Field Of Machine Learning
• Secret Sharing
• Federated Learning
• Weak Supervision
• Amount Of Labels
• AlphaGo
• Decoding
• Taylor Series
• Hidden Representation
• Matrix Multiplication
• Target Domain
• Logistic Loss
• Low-level Features
• Stacked Autoencoder
• Alignment Loss
• Layer Of Autoencoder
• Accuracy Loss
• Preprocessing Phase
• Multi-party Computation
• Homomorphic Encryption