arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.04309cs.LGcs.DC
收藏

纵向联邦学习:挑战、方法与实验

Vertical Federated Learning: Challenges, Methodologies and Experiments

School of Electrical and Optical Engineering, Nanjing University of Science and Technology(南京理工大学电气与光学工程学院);Data61, CSIRO(澳大利亚联邦科学与工业研究组织数据61分部);China Academy of Information and Communication Technology (CAICT)(中国信息通信研究院);Shanghai Jiao Tong University(上海交通大学);Nanjing University(南京大学)

Kang Wei, Jun Li, Chuan Ma, Ming Ding, Sha Wei, Fan Wu, Guihai Chen, Thilina Ranbaduge

AI总结:

本文提出VFL通用框架,系统梳理隐私安全、计算通信、模型分割与系统异构四类挑战,并给出解决方案和真实数据集实验验证。

摘要:

近年来,由于终端用户设备的计算与感知能力不断提升,同时用户隐私担忧日益加剧,联邦学习(FL)已成为一种颇具前景的分布式机器学习(ML)技术。作为FL中的一种特殊架构,纵向FL(VFL)能够通过整合来自不同客户端的子模型来构建一个超级ML模型。这些子模型利用具有不同属性的纵向划分数据在本地进行训练。因此,VFL的设计与传统FL存在根本差异,从而带来了新的、独特的研究问题。本文旨在讨论VFL中的关键挑战及有效解决方案,并在真实数据集上开展实验,以阐明这些问题。具体而言,我们首先提出一个关于VFL的通用框架,并强调VFL与传统FL之间的关键区别。随后,我们从四个方面讨论根植于VFL系统的研究挑战,即安全与隐私风险、高昂的计算与通信成本、模型分割可能造成的结构性损害,以及系统异构性。之后,我们开发了应对上述挑战的解决方案,并开展大量实验以展示所提解决方案的有效性。

英文摘要:

Recently, federated learning (FL) has emerged as a promising distributed machine learning (ML) technology, owing to the advancing computational and sensing capacities of end-user devices, however with the increasing concerns on users' privacy. As a special architecture in FL, vertical FL (VFL) is capable of constructing a hyper ML model by embracing sub-models from different clients. These sub-models are trained locally by vertically partitioned data with distinct attributes. Therefore, the design of VFL is fundamentally different from that of conventional FL, raising new and unique research issues. In this paper, we aim to discuss key challenges in VFL with effective solutions, and conduct experiments on real-life datasets to shed light on these issues. Specifically, we first propose a general framework on VFL, and highlight the key differences between VFL and conventional FL. Then, we discuss research challenges rooted in VFL systems under four aspects, i.e., security and privacy risks, expensive computation and communication costs, possible structural damage caused by model splitting, and system heterogeneity. Afterwards, we develop solutions to addressing the aforementioned challenges, and conduct extensive experiments to showcase the effectiveness of our proposed solutions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑