Vertical Federated Learning: Concepts, Advances and Challenges

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Yang, Kang, Yan, Zou, Tianyuan, Pu, Yanhong, He, Yuanqin, Ye, Xiaozhou, Ouyang, Ye, Zhang, Ya-Qin, Yang, Qiang
Format: Preprint
Publié: 2022
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910318029963264
author Liu, Yang
Kang, Yan
Zou, Tianyuan
Pu, Yanhong
He, Yuanqin
Ye, Xiaozhou
Ouyang, Ye
Zhang, Ya-Qin
Yang, Qiang
author_facet Liu, Yang
Kang, Yan
Zou, Tianyuan
Pu, Yanhong
He, Yuanqin
Ye, Xiaozhou
Ouyang, Ye
Zhang, Ya-Qin
Yang, Qiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2211_12814
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Vertical Federated Learning: Concepts, Advances and Challenges
Liu, Yang
Kang, Yan
Zou, Tianyuan
Pu, Yanhong
He, Yuanqin
Ye, Xiaozhou
Ouyang, Ye
Zhang, Ya-Qin
Yang, Qiang
Machine Learning
Artificial Intelligence
Cryptography and Security
Distributed, Parallel, and Cluster Computing
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.
title Vertical Federated Learning: Concepts, Advances and Challenges
topic Machine Learning
Artificial Intelligence
Cryptography and Security
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2211.12814