2,822 Hits in 4.2 sec

Cross-Silo Federated Learning: Challenges and Opportunities [article]

Chao Huang, Jianwei Huang, Xin Liu
2022 arXiv   pre-print
We then provide a systematic overview of the existing approaches to the challenges in cross-silo FL by focusing on their connections and differences to cross-device FL.  ...  More specifically, we first discuss applications of cross-silo FL and outline its major challenges.  ...  PRIVACY AND SECURITY For cross-silo FL to gain trust and be widely adopted in practice, its privacy and security implications must be well understood and taken care of.  ... 
arXiv:2206.12949v1 fatcat:emc4wbfdfrey5p2zivc66yugsm

Advances and Open Problems in Federated Learning

Peter Kairouz, H. Brendan McMahan
2021 Foundations and Trends® in Machine Learning  
We term these two federated learning settings "cross-device" and "cross-silo" respectively.  ...  It embodies the principles of focused collection and data minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning.  ... 
doi:10.1561/2200000083 fatcat:zp4g5k3p6jgfzimh2wt4bp562y

The Role of Cross-Silo Federated Learning in Facilitating Data Sharing in the Agri-Food Sector [article]

Aiden Durrant, Milan Markovic, David Matthews, David May, Jessica Enright, Georgios Leontidis
2021 arXiv   pre-print
However, recent machine learning advances, e.g. federated learning and privacy-preserving technologies, can offer a solution to this issue via providing the infrastructure and underpinning technologies  ...  In this paper, we propose a technical solution based on federated learning that uses decentralized data, (i.e. data that are not exchanged or shared but remain with the owners) to develop a cross-silo  ...  The latter is known as cross-silo federated learning and specifically differs from cross-device by the quantity, size and availability of the participants data.  ... 
arXiv:2104.07468v1 fatcat:kpnn66urhra7vn3pgycutcxo5m

Federated Learning for Privacy-Preserving Open Innovation Future on Digital Health [article]

Guodong Long, Tao Shen, Yue Tan, Leah Gerrard, Allison Clarke, Jing Jiang
2021 arXiv   pre-print
Federated learning is a new machine learning paradigm to learn a shared model across users or organisations without direct access to the data.  ...  Existing challenges and solutions for federated learning will be discussed.  ...  Transfer learning for cross-silo federated learning Existing medical data is not fully exploited by traditional machine learning methods because it sits in data silos and privacy concerns restrict access  ... 
arXiv:2108.10761v1 fatcat:lp4wuhb4sre7toacoba6upfcxq

Subject Membership Inference Attacks in Federated Learning [article]

Anshuman Suri, Pallika Kanani, Virendra J. Marathe, Daniel W. Peterson
2022 arXiv   pre-print
We design a simulator for generating various synthetic federation configurations, enabling us to study how properties of the data, model design and training, and the federation itself impact subject privacy  ...  Privacy in Federated Learning (FL) is studied at two different granularities: item-level, which protects individual data points, and user-level, which protects each user (participant) in the federation  ...  Membership Inference Privacy attacks are a common approach used to assess privacy risks in machine learning.  ... 
arXiv:2206.03317v1 fatcat:fa7uezezrnaf5fguib2eyhfbae

Federated Learning: Balancing the Thin Line Between Data Intelligence and Privacy [article]

Sherin Mary Mathews, Samuel A. Assefa
2022 arXiv   pre-print
This article provides a systematic overview and detailed taxonomy of federated learning.  ...  Potential candidate areas for federated learning, including IoT ecosystem, healthcare applications, are discussed with a particular focus on banking and financial domains.  ...  Cross-silo federated learning is more flexible than cross-device federated learning (Zhang et al. 2020) .  ... 
arXiv:2204.13697v1 fatcat:rvlsrnk66jblzguy2vnh3thgtu

Differential Privacy-enabled Federated Learning for Sensitive Health Data [article]

Olivia Choudhury, Aris Gkoulalas-Divanis, Theodoros Salonidis, Issa Sylla, Yoonyoung Park, Grace Hsu, Amar Das
2020 arXiv   pre-print
sensitive data, resource constraints for transferring and integrating data from multiple sites, and risk of a single point of failure.  ...  Leveraging real-world health data for machine learning tasks requires addressing many practical challenges, such as distributed data silos, privacy concerns with creating a centralized database from person-specific  ...  Federated learning (FL) offers a new paradigm for training a global machine learning model from data distributed across multiple data silos, eliminating the need for raw data sharing [14] .  ... 
arXiv:1910.02578v3 fatcat:7okfkjznyvb6fdway4attytbxe

On Privacy and Personalization in Cross-Silo Federated Learning [article]

Ziyu Liu, Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
2022 arXiv   pre-print
While the application of differential privacy (DP) has been well-studied in cross-device federated learning (FL), there is a lack of work considering DP for cross-silo FL, a setting characterized by a  ...  We provide a thorough empirical study of competing methods as well as a theoretical characterization of MR-MTL for a mean estimation problem, highlighting the interplay between privacy and cross-silo data  ...  We thank Sebastian Caldas, Tian Li, Yash Savani, and Amrith Setlur at CMU and Peter Kairouz at Google for helpful discussions and feedback.  ... 
arXiv:2206.07902v1 fatcat:lad6h3km4jfyhoekeietofcj7e

FedVoting: A Cross-Silo Boosting Tree Construction Method for Privacy-Preserving Long-Term Human Mobility Prediction

Yinghao Liu, Zipei Fan, Xuan Song, Ryosuke Shibasaki
2021 Sensors  
Compared with training the model independently for each silo (organization) and state-of-art baselines, the FedVoting method achieves a significant accuracy improvement, almost comparable to the centralized  ...  Thus, the method of federated learning (FL) can be adopted, in which multiple entities collaborate to train a collective model with their raw data stored locally and, therefore, not exchanged or transferred  ...  Cross-silo federated learning means the participants are organizations (e.g., companies and data centers) with large volumes of data, while cross-device federated learning consists of a very large number  ... 
doi:10.3390/s21248282 pmid:34960376 pmcid:PMC8708522 fatcat:57vbraqrzbhnhefm6dzzmu77ge

Privacy-first health research with federated learning [article]

John B Hernandez, Adam Sadilek, Luyang Liu, Dung Nguyen, Methun Kamruzzaman, Benjamin Rader, Alex Ingerman, Stefan Mellem, Peter Kairouz, Elaine O Nsoesie, Jamie MacFarlane, Anil Vullikanti (+4 others)
2020 medRxiv   pre-print
This work is the first to apply modern and general federated learning methods to clinical and epidemiological research -- across a spectrum of units of federation and model architectures.  ...  Recent advances in federated learning enable building complex machine-learned models that are trained in a distributed fashion.  ...  The two approaches are termed "cross-device" and "cross-silo" federated learning respectively, and are described in-depth in Kairouz et al. (2019 ) .  ... 
doi:10.1101/2020.12.22.20245407 fatcat:zcz62aiirndwzf47q4dvstgbr4

Artificial intelligence across company borders [article]

Olga Fink, Torbjørn Netland, Stefan Feuerriegel
2021 arXiv   pre-print
In this Viewpoint, we discuss the use, value, and implications of this approach in a cross-company setting.  ...  Combining federated learning with domain adaptation can provide a solution to this problem by enabling effective cross-company AI without data disclosure.  ...  Examples include trust, cybersecurity risks, ethical constraints, and laws for ensuring a user's right to privacy.  ... 
arXiv:2107.03912v1 fatcat:vfk7mmbbnrc6nbing63vyy7uau

Blockchain-Enabled 5G Edge Networks and Beyond: An Intelligent Cross-Silo Federated Learning Approach

Sandi Rahmadika, Muhammad Firdaus, Seolah Jang, Kyung-Hyune Rhee, Jinwei Wang
2021 Security and Communication Networks  
Furthermore, the blockchain is an immutable data approach that can be leveraged for FL across 5G ENs and beyond.  ...  The advantage of edge networks is their pioneering integration of other prominent technologies such as blockchain and federated learning (FL) to produce better services on wireless networks.  ...  Hence, federated learning (FL) is offered as a new approach, with the main purpose of protecting UE privacy by building machine learning models without the need to centralize the training data on a central  ... 
doi:10.1155/2021/5550153 fatcat:qbpkafrxyzgqlhr6423ldqyolq

Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning [article]

Jun Luo, Shandong Wu
2022 arXiv   pre-print
Conventional federated learning (FL) trains one global model for a federation of clients with decentralized data, reducing the privacy risk of centralized training.  ...  In this work, we propose APPLE, a personalized cross-silo FL framework that adaptively learns how much each client can benefit from other clients' models.  ...  (Pittsburgh Center for AI Innovation in Medical Imaging), and an Amazon AWS Machine Learning Research Award.  ... 
arXiv:2110.08394v3 fatcat:yxodq7lyffetfp3ug36xrwjc5y

A Field Guide to Federated Optimization [article]

Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, Blaise Aguera y Arcas, Maruan Al-Shedivat, Galen Andrew, Salman Avestimehr, Katharine Daly, Deepesh Data, Suhas Diggavi (+41 others)
2021 arXiv   pre-print
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection.  ...  The distributed learning process can be formulated as solving federated optimization problems, which emphasize communication efficiency, data heterogeneity, compatibility with privacy and system requirements  ...  During the discussion, a general consensus about the need for a guide about federated optimization is reached.  ... 
arXiv:2107.06917v1 fatcat:lfpi4c3s45gl7aezwulaczzev4

Advances and Open Problems in Federated Learning [article]

Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G.L. D'Oliveira, Hubert Eichner (+47 others)
2021 arXiv   pre-print
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science  ...  Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service  ...  Acknowledgments The authors would like to thank Alex Ingerman and David Petrou for their useful suggestions and insightful comments during the review process.  ... 
arXiv:1912.04977v3 fatcat:efkbqh4lwfacfeuxpe5pp7mk6a
« Previous Showing results 1 — 15 out of 2,822 results