- DOI: 10.48550/arXiv.2212.00622
- Corpus ID: 254125648
Vertical Federated Learning: A Structured Literature Review
- Afsana Khan , M. T. Thij , A. Wilbik
- Published in arXiv.org 1 December 2022
- Computer Science
Figures and Tables from this paper
4 Citations
Vertical federated learning for effectiveness, security, applicability: a survey, a survey of privacy threats and defense in vertical federated learning: from model life cycle perspective, p3ls: partial least squares under privacy preservation, explainable artificial intelligence (xai) 2.0: a manifesto of open challenges and interdisciplinary research directions, 104 references, vertical federated learning: taxonomies, threats, and prospects, communication-efficient vertical federated learning, data pricing in vertical federated learning, vf-ps: how to select important participants in vertical federated learning, efficiently and securely, label inference attacks against vertical federated learning, multi-vfl: a vertical federated learning system for multiple data and label owners, beyond model splitting: preventing label inference attacks in vertical federated learning with dispersed training, practical vertical federated learning with unsupervised representation learning.
- Highly Influential
Multi-Participant Multi-Class Vertical Federated Learning
Implementing vertical federated learning using autoencoders: practical application, generalizability, and utility study, related papers.
Showing 1 through 3 of 0 Related Papers
Published in arXiv.org 2022
Afsana Khan M. T. Thij A. Wilbik
A Vertical Federation Framework Based on Representation Learning
- Conference paper
- First Online: 01 January 2022
- Cite this conference paper
- Yin Zhang 5 ,
- Fanglin An 5 &
Part of the book series: Lecture Notes on Data Engineering and Communications Technologies ((LNDECT,volume 103))
1174 Accesses
Vertical federated learning aims to use different attribute sets of the same user to jointly build a model without disclosing its original data or model parameters. Facing the challenges brought by massive data in the Internet of Things, based on representation learning, advanced features are accurately and efficiently extracted to prepare for downstream tasks. At the same time, when implementing federated learning in the Internet of Things environment, it is necessary to consider the computing power of a large number of edge devices. In real life, more non-Euclidean data is used. For non-Euclidean data, we use graph neural networks as encoders to obtain better high-level feature vectors with fewer parameters. We propose a new vertical federated learning framework based on representation learning, combined with graph neural networks, to build a better model in the massive non-Euclidean data of the Internet of Things, while protecting the data privacy of each data owner.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Subscribe and save.
- Get 10 units per month
- Download Article/Chapter or Ebook
- 1 Unit = 1 Article or 1 Chapter
- Cancel anytime
- Available as PDF
- Read on any device
- Instant download
- Own it forever
- Available as EPUB and PDF
- Compact, lightweight edition
- Dispatched in 3 to 5 business days
- Free shipping worldwide - see info
Tax calculation will be finalised at checkout
Purchases are for personal use only
Institutional subscriptions
Similar content being viewed by others
Engineering Federated Learning Systems: A Literature Review
A Federated Learning Algorithms Development Paradigm
FeDZIO: Decentralized Federated Knowledge Distillation on Edge Devices
Zhang F, Kuang K, You Z et al (2020) Federated unsupervised representation learning. arXiv preprint arXiv:2010.08982
Chen C, Hu W, Xu Z et al (2021) FedGL: federated graph learning framework with global self-supervision. arXiv preprint arXiv:2105.03170
Brendan McMahan H, Moore E, Ramage D et al (2016) Communication-efficient learning of deep networks from decentralized data. arXiv. arXiv: 1602.05629
Google Scholar
Shokri R, Shmatikov V (2015) Privacy-preserving deep learning. In: Proceedings of the 22nd ACM SIGSAC conference on computer and communications security, pp 1310–1321
Smith V, Chiang CK, Sanjabi M et al. Federated multi-task learning. Adv Neural Inf Process Syst 4424–4434
Hitaj B, Ateniese G, Perez-Cruz F (2017) Deep models under the GAN: information leakage from collaborative deep learning. In: Proceedings of the 2017 ACM SIGSAC conference on computer and communications security, pp 603–618
Jin Y, Wei X, Liu Y et al (2020) Towards utilizing unlabeled data in federated learning: a survey and prospective. arXiv preprint arXiv:2002.11545
van Berlo B, Saeed A, Ozcelebi T (2020) Towards federated unsupervised representation learning. In: Proceedings of the third ACM international workshop on edge systems, analytics and networking, pp 31–36
Wang T, Isola P (2020) Understanding contrastive representation learning through alignment and uniformity on the hyper sphere. In: International conference on machine learning. PMLR, pp 9929–9939
Yang Q, Liu Y, Chen T et al (2019) Federated machine learning: concept and applications. ACM Trans Intell Syst Technol (TIST) 10(2):1–19
Article Google Scholar
Chen T, Kornblith S, Norouzi M et al (2020) A simple framework for contrastive learning of visual representations. In: International conference on machine learning. PMLR, pp 1597–1607
Download references
Acknowledgements
The National Natural Science Foundation of China (62162020).
Author information
Authors and affiliations.
School of Cyberspace Security, Hainan University, Haikou, China
Yin Zhang, Fanglin An & Jun Ye
You can also search for this author in PubMed Google Scholar
Corresponding author
Correspondence to Jun Ye .
Editor information
Editors and affiliations.
School of Computer Science, Univ of Oklahoma, Sch of Comp Science, Norman, OK, USA
Mohammed Atiquzzaman
University of Aizu, Aizuwakamatsu, Japan
Shanghai Polytechnic University, Shanghai, China
Rights and permissions
Reprints and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper.
Zhang, Y., An, F., Ye, J. (2022). A Vertical Federation Framework Based on Representation Learning. In: Atiquzzaman, M., Yen, N., Xu, Z. (eds) 2021 International Conference on Big Data Analytics for Cyber-Physical System in Smart City. Lecture Notes on Data Engineering and Communications Technologies, vol 103. Springer, Singapore. https://doi.org/10.1007/978-981-16-7469-3_70
Download citation
DOI : https://doi.org/10.1007/978-981-16-7469-3_70
Published : 01 January 2022
Publisher Name : Springer, Singapore
Print ISBN : 978-981-16-7468-6
Online ISBN : 978-981-16-7469-3
eBook Packages : Intelligent Technologies and Robotics Intelligent Technologies and Robotics (R0)
Share this paper
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative
- Publish with us
Policies and ethics
- Find a journal
- Track your research
IMAGES
VIDEO
COMMENTS
In this paper, we present a structured literature review discussing the state-of-the-art approaches in VFL. Additionally, the literature review highlights the existing solutions to challenges in VFL and provides potential research directions in this domain.
In this paper, we present a structured literature review discussing the state-of-the-art approaches in VFL. Addition- ally, the literature review highlights the existing solutions to challenges in VFL and provides potential research directions in this domain.
Federated Learning (FL) can be categorized into three architectures: Vertical Federated Learning, Horizontal Federated Learning, and Federated Transfer Learning.
In this paper, we present a structured literature review discussing the state-of-the-art approaches in VFL. Additionally, the literature review highlights the existing solutions to challenges in VFL and provides potential research directions in this domain.
The topic centered around data distributions and heterogeneity allowed researchers to introduce different categories of FL which are horizontal federated learning, vertical federated learning, and federated transfer learning.
The idea of FL is to enable collaborating participants train machine learning (ML) models on decentralized data without breaching privacy. In simpler words, federated learning is the approach of ``bringing the model to the data, instead of bringing the…
Federated Learning (FL) is a collaboratively decentralized privacy-preserving technology to overcome challenges of data silos and data sensibility. Exactly what research is carrying the research momentum forward is a question of interest to research communities as well as industrial engineering.
Fig. 1: Types of Federated Learning - "Vertical Federated Learning: A Structured Literature Review"
Vertical federated learning is a paradigm of Federated Learning (FL), which aims to build a model by using different attribute sets of the same user to build a federated learning model based on distributed data sets.
This survey paper offers an exhaustive and systematic review of federated learning, emphasizing its categories, challenges, aggregation techniques, and associated development tools.