Filters








645 Hits in 6.2 sec

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

Chao Huang, Jianwei Huang, Xin Liu
2022 arXiv   pre-print
Based on the participating clients and the model training scale, federated learning can be classified into two types: cross-device FL where clients are typically mobile devices and the client number can  ...  More specifically, we first discuss applications of cross-silo FL and outline its major challenges.  ...  For example, the federated learning process for next word prediction is embedded in the mobile applications and automatically executed by Google.  ... 
arXiv:2206.12949v1 fatcat:emc4wbfdfrey5p2zivc66yugsm

Personalised Federated Learning: A Combinational Approach [article]

Sone Kyaw Pye, Han Yu
2021 arXiv   pre-print
and knowledge distillation.  ...  Federated learning (FL) is a distributed machine learning approach involving multiple clients collaboratively training a shared model.  ...  Engineering Programmatic Fund (A20G8b0102), Singapore; the SDU-NTU Centre for AI Research (C-FAIR), Shandong University, China.  ... 
arXiv:2108.09618v1 fatcat:bhw374jivrcvpa6mxzwrsixwcq

A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection [article]

Qinbin Li, Zeyi Wen, Zhaomin Wu, Sixu Hu, Naibo Wang, Yuan Li, Xu Liu, Bingsheng He
2021 arXiv   pre-print
Moreover, we provide a thorough categorization for federated learning systems according to six different aspects, including data distribution, machine learning model, privacy mechanism, communication architecture  ...  , scale of federation and motivation of federation.  ...  Acknowledgement This work is supported by a MoE AcRF Tier 1 grant (T1 251RES1824), an SenseTime Young Scholars Research Fund, and a MOE Tier 2 grant (MOE2017-T2-1-122) in Singapore.  ... 
arXiv:1907.09693v6 fatcat:d3l2l664mjdfrjgyok43pfxnvq

Decentral and Incentivized Federated Learning Frameworks: A Systematic Literature Review [article]

Leon Witt, Mathis Heyer, Kentaroh Toyoda, Wojciech Samek, Dan Li
2022 arXiv   pre-print
The advent of Federated Learning (FL) has ignited a new paradigm for parallel and confidential decentralized Machine Learning (ML) with the potential of utilizing the computational power of a vast number  ...  Yet, in order to scale this new paradigm beyond small groups of already entrusted entities towards mass adoption, the Federated Learning Framework (FLF) has to become (i) truly decentralized and (ii) participants  ...  Not applicable True False CS cross-silo (few clients ) CD cross-device (many clients ) 40 et al. propose a FLF for a knowledge trading marketplace where vehicles can buy and sell models that vary geographically  ... 
arXiv:2205.07855v2 fatcat:ds2wavc33nd5jdw462l2vuddya

FLRA: A Reference Architecture for Federated Learning Systems [article]

Sin Kit Lo, Qinghua Lu, Hye-Young Paik, Liming Zhu
2021 arXiv   pre-print
Hence, developing a federated learning system requires both software system design thinking and machine learning knowledge.  ...  In this paper, we propose FLRA, a reference architecture for federated learning systems, which provides a template design for federated learning-based solutions.  ...  transfer federated learning) and device partitioning (e.g., cross-device, cross-silo), the ownership and security requirements of different client devices, the system heterogeneity, and the participation  ... 
arXiv:2106.11570v1 fatcat:fh37vlxbh5gvlas5chi7ikuq2q

Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning [article]

Shaoxiong Ji and Teemu Saravirta and Shirui Pan and Guodong Long and Anwar Walid
2021 arXiv   pre-print
Federated learning is a new learning paradigm that decouples data collection and model training via multi-party computation and model aggregation.  ...  transfer learning, unsupervised learning, and reinforcement learning.  ...  Applications of cross-silo federated learning, including healthcare and financial applications, have practical significance. We recommend the survey by Xu et al.  ... 
arXiv:2102.12920v2 fatcat:5fcwfhxibbedbcbuzrfyqdedky

An Exploratory Analysis on Users' Contributions in Federated Learning

Jiyue Huang, Rania Talbi, Zilong Zhao, Sara Boucchenak, Lydia Y. Chen, Stefanie Roos
2020 2020 Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)  
Federated Learning is an emerging distributed collaborative learning paradigm adopted by many of today's applications, e.g., keyboard prediction and object recognition.  ...  In this paper, we aim to answer how well incentives recognize (in)accurate local models from honest and malicious users, and perceive their impacts on the model accuracy of federated learning systems.  ...  This a hardware-based protection mechanism that is mostly adapted to cross-silo 2 federated learning ecosystems where the local training code on the participants-side is implemented in a Trusted Execution  ... 
doi:10.1109/tps-isa50397.2020.00014 fatcat:ey4zo4htwfcybg5euc2axtkqtq

An Exploratory Analysis on Users' Contributions in Federated Learning [article]

Jiyue Huang, Rania Talbi, Zilong Zhao, Sara Boucchenak, Lydia Y. Chen, Stefanie Roos
2020 arXiv   pre-print
Federated Learning is an emerging distributed collaborative learning paradigm adopted by many of today's applications, e.g., keyboard prediction and object recognition.  ...  In this paper, we aim to answer how well incentives recognize (in)accurate local models from honest and malicious users, and perceive their impacts on the model accuracy of federated learning systems.  ...  This a hardware-based protection mechanism that is mostly adapted to cross-silo 2 federated learning ecosystems where the local training code on the participants-side is implemented in a Trusted Execution  ... 
arXiv:2011.06830v1 fatcat:hn5utzq2nvh5tlmmroiw6wqb7y

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.  ...  AWS Machine Learning Research Award.  ... 
arXiv:2110.08394v3 fatcat:yxodq7lyffetfp3ug36xrwjc5y

A Decision Model for Federated Learning Architecture Pattern Selection [article]

Sin Kit Lo, Qinghua Lu, Hye-Young Paik, Liming Zhu
2022 arXiv   pre-print
Therefore, in this paper, we present a set of decision models to assist designers and architects who have limited knowledge in federated learning, in selecting architectural patterns for federated learning  ...  Federated learning is growing fast in both academia and industry to resolve data hungriness and privacy issues in machine learning.  ...  The participant also questioned the applicability of the decision models on cross-silo federated learning scenarios.  ... 
arXiv:2204.13291v1 fatcat:yzm2437kjnernizw5ehzrsyoby

Reward Systems for Trustworthy Medical Federated Learning [article]

Konstantin D. Pandl, Florian Leiser, Scott Thiebes, Ali Sunyaev
2022 arXiv   pre-print
Federated learning (FL) has received high interest from researchers and practitioners to train machine learning (ML) models for healthcare. Ensuring the trustworthiness of these models is essential.  ...  Our work helps researchers and practitioners design reward systems for FL with well-aligned incentives for trustworthy ML.  ...  ACKNOWLEDGMENT The authors acknowledge support by the state of Baden-Württemberg through bwHPC and the German Research Foundation (DFG) through grant INST 35/1134-1 FUGG.  ... 
arXiv:2205.00470v1 fatcat:otl2wj5yjffrbgkha3txyzdbbi

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
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  ...  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  ...  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

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI [article]

Jiangchao Yao, Shengyu Zhang, Yang Yao, Feng Wang, Jianxin Ma, Jianwei Zhang, Yunfei Chu, Luo Ji, Kunyang Jia, Tao Shen, Anpeng Wu, Fengda Zhang (+6 others)
2022 arXiv   pre-print
In this survey, we conduct a systematic review for both cloud and edge AI.  ...  Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism.  ...  In cross-silo FL, differently, there are organizations where data silos naturally exist.  ... 
arXiv:2111.06061v3 fatcat:5rq6s5s4cvcidblidgahwynp34

Cross-Silo Heterogeneous Model Federated Multitask Learning [article]

Xingjian Cao, Zonghang Li, Gang Sun, Hongfang Yu, Mohsen Guizani
2022 arXiv   pre-print
Participants utilizing cross-silo federated learning (CS-FL) settings are independent organizations with different task needs, and they are concerned not only with data privacy but also with independently  ...  In this study, we present a novel federated learning method CoFED based on unlabeled data pseudolabeling via a process known as cotraining.  ...  and Applications (PCL2018KP001).  ... 
arXiv:2202.08603v5 fatcat:ekae2bqsrbe2pjerownor4ebaq

Challenges, Applications and Design Aspects of Federated Learning: A Survey

K M Jawadur Rahman, Faisal Ahmed, Nazma Akhter, Mohammad Hasan, Ruhul Amin, Kazi Ehsan Aziz, A.K.M. Muzahidul Islam, Md Saddam Hossain Mukta, A.K.M. Najmul Islam
2021 IEEE Access  
Federated Learning (FL) is a new technology that has been a hot research topic.  ...  There are many application domains where large amounts of properly labeled and complete data are not available in a centralized location, for example, doctors' diagnosis from medical image analysis.  ...  architecture, and cross-silo [75] vs cross-device [76] , [77] FL for scale of federation are the other challenges and approaches discussed here.  ... 
doi:10.1109/access.2021.3111118 fatcat:jsdaxx6mvjdrrhomeknujwsj7i
« Previous Showing results 1 — 15 out of 645 results