Asymmetrical Vertical Federated Learning
By Yang Liu, Xiong Zhang, Libin Wang. 2020
53 citations recorded by the source corpus.
Federated learning is a distributed machine learning method that aims to preserve the privacy of sample features and labels. In a federated learning system, ID-based sample alignment approaches are usually applied with few efforts made on the protection of ID privacy. In real-life applications, however, the confidentiality of sample IDs, which are the strongest row identifiers, is also drawing much attention from many participants. To relax their privacy concerns about ID privacy, this paper formally proposes the notion of asymmetrical vertical federated learning and illustrates the way to protect sample IDs. The standard private set intersection protocol is adapted to achieve the asymmetrical ID alignment phase in an asymmetrical vertical federated learning system. Correspondingly, a Pohlig-Hellman realization of the adapted protocol is provided. This paper also presents a genuine with dummy approach to achieving asymmetrical federated model training. To illustrate its application, a federated logistic regression algorithm is provided as an example. Experiments are also made for validating the feasibility of this approach.
Subfields: Artificial Intelligence
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
- Qiang Yang
- Murali Annavaram
- Chaoyang He
- Yang Liu
- S. Avestimehr
- Tianjian Chen
- Praneeth Vepakomma
- Abhishek Singh
Citations in the corpus
- FedML: A Research Library and Benchmark for Federated Machine Learning (2020, background): “As demonstrated in Figure 3, FL has various topology definitions, such as vertical FL [34, 35, 36, 37, 38, 39, 40], split learning [41, 42], decentralized FL [43, 44, 45, 46], and Hierarchical FL [47, 48, 49, 50, 51, 52].”
- Vertical Federated Learning: Concepts, Advances, and Challenges (2022, methodology): “[91] proposed an adapted PSI protocol for asymmetrical ID alignment using a Pohlig-Hellman encryption scheme and an obfuscate set to help protect the entity information of a weaker party with far fewer samples than the other party from being exposed.”
- Federated Multi-view Learning for Private Medical Data Integration and Analysis (2021, background): “proposed asymmetrical vertical federated learning and showed the way to achieve the asymmetrical ID alignment [41].”
- Self-supervised Cross-silo Federated Neural Architecture Search (2021, background): “[31] studied the asymmetrical vertical federated learning problem, where different participants have non-identical privacy concerns over the samples ID.”