A Secure Federated Transfer Learning Framework

By Yang Liu, Yan Kang, Chaoping Xing, Tianjian Chen, Qiang Yang. 2020

549 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Federated & Distributed Learning, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yang Liu
2. Qiang Yang
3. Jiankun Hu
4. Yanming Zhu
5. Xuefei Yin
6. Bingsheng He
7. Qinbin Li
8. Tianjian Chen

In Federated & Distributed Learning

1. Yang Liu
2. Qiang Yang
3. Bingsheng He
4. Qinbin Li
5. Tianjian Chen
6. Yan Kang
7. Jiankun Hu
8. Yanming Zhu

In Privacy & Security

1. Yang Liu
2. Yan Kang
3. Qiang Yang
4. Bingsheng He
5. Qinbin Li
6. Tianjian Chen
7. Kang G. Shin
8. Yong Cheng

Citations in the corpus

• SecureBoost: A Lossless Federated Learning Framework (2019, background): “and protocols are proposed for linear models(5,13) and neural networks.(26) Some previous works have been proposed for privacy-preserving decision trees over vertically partitioned data.”
• Federated User Representation Learning (2019, background): “Personalization in FL poses many challenges due to its distributed nature, high communication costs, and privacy constraints [17, 5, 6, 19, 18, 20, 32, 12].”
• Federated Learning on Non-IID Data Silos: An Experimental Study (2021, background): “It has attracted many research interests [9], [25], [35], [42], [45], [52], [75] and been widely used in practice [5], [23], [34].”
• A Full Dive Into Realizing the Edge-Enabled Metaverse: Visions, Enabling Technologies, and Challenges (2022, background): “training is conducted on the labeled data stored on local devices [301]–[304].”
• Vertical Federated Learning: Concepts, Advances, and Challenges (2022, methodology): “SFTL [24] designs a HE-based protocol and an SS-based protocol, respectively, to encrypt information shared between two parties that adopt neural networks with one or two layers.”
• Federated Multi-view Learning for Private Medical Data Integration and Analysis (2021, background): “Liu et al. proposed an end-to-end approach to the FTL problem and demonstrated it was comparable to transfer learning without privacy protection [36].”
• Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study (2019, background): “Federated transfer learning (FTL) [188] provides a safer and more reliable approach for specific industries.”
• A Comprehensive Survey of Privacy-preserving Federated Learning (2021, background): “WHO RA1 [61, 196, 228] [26, 137, 218] [157, 169, 198] [144, 164, 199] [63, 70, 193] [16, 174, 191] [78, 110, 228] [52, 81, 216] [32, 56, 222] [30, 127, 173] RA2 [114, 175, 187] [215, 221, 224] [29, 111, 113] [13, 199] [3, 10, 40] [109, 155, 168] [45, 172, 193] [20, 52, 57] [56, 165, 197] [173, 199, ”
• Self-supervised Cross-silo Federated Neural Architecture Search (2021, background): “[1], [8]; 2) Vertical Federated Learning (VFL): VFL describes the scenarios where different organizations with a common set of users train a cooperative model to better utilize the data with distributed features [2], [9]–[12]; 3) Federated Transfer Learning (FTL): FTL applies to the cases where the ”