Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Vertical Federated Learning: Concepts, Advances and Challenges

About

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.

Yang Liu, Yan Kang, Tianyuan Zou, Yanhong Pu, Yuanqin He, Xiaozhou Ye, Ye Ouyang, Ya-Qin Zhang, Qiang Yang• 2022

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-10 (test)
Accuracy93.89
410
Image ClassificationEMNIST (test)
Accuracy94.51
234
Showing 2 of 2 rows

Other info

Follow for update