70,302 Hits in 4.6 sec

Federated Optimization in Heterogeneous Networks [article]

Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith
2020 arXiv   pre-print
In this work, we introduce a framework, FedProx, to tackle heterogeneity in federated networks.  ...  on each device in the network (systems heterogeneity), and (2) non-identically distributed data across the network (statistical heterogeneity).  ...  Our proposed framework provides improved robustness and stability for optimization in heterogeneous federated networks.  ... 
arXiv:1812.06127v5 fatcat:ol4wcatdynetldegch45wkppia

On the Performance of Federated Learning Algorithms for IoT

Mehreen Tahir, Muhammad Intizar Ali
2022 IoT  
We have also conducted a comparative analysis of the top available federated algorithms over a heterogeneous dynamic IoT network.  ...  claim to mitigate the negative impact of heterogeneity in FL networks, unfortunately, the effectiveness of these proposed solutions has never been studied and quantified.  ...  In contrast, [20] presented the Dispersed Federated Learning (DFL) framework to provide resource optimization for FL networks.  ... 
doi:10.3390/iot3020016 fatcat:lh5eolf2d5e3vbqdpknypuuf4u

Federated Learning: Challenges, Methods, and Future Directions [article]

Tian Li, Anit Kumar Sahu, Ameet Talwalkar, Virginia Smith
2019 arXiv   pre-print
Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization  ...  In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant  ...  Research Faculty Award, a Carnegie Bosch Institute Research Award and the CONIX Research Center, one of six centers in JUMP, a Semiconductor Research Corporation (SRC) program sponsored by DARPA.  ... 
arXiv:1908.07873v1 fatcat:pcztnmhquvd65es6wdz34igbhi

SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging [article]

Miao Zhang, Liangqiong Qu, Praveer Singh, Jayashree Kalpathy-Cramer, Daniel L. Rubin
2022 arXiv   pre-print
In this study, we propose a novel heterogeneity-aware federated learning method, SplitAVG, to overcome the performance drops from data heterogeneity in federated learning.  ...  Unlike previous federated methods that require complex heuristic training or hyper parameter tuning, our SplitAVG leverages the simple network split and feature map concatenation strategies to encourage  ...  In this study, we develop a heterogeneity-aware optimization platform, SplitAVG, to address the challenge of data heterogeneity in federated learning methods.  ... 
arXiv:2107.02375v5 fatcat:gaqpo5ftrjemhibffhwhqxhrqe

Federated Learning for 6G Communications: Challenges, Methods, and Future Directions [article]

Yi Liu, Xingliang Yuan, Zehui Xiong, Jiawen Kang, Xiaofei Wang, Dusit Niyato
2020 arXiv   pre-print
It is generally believed that 6G will be established on ubiquitous Artificial Intelligence (AI) to achieve data-driven Machine Learning (ML) solutions in heterogeneous and massive-scale networks.  ...  In this article, we first introduce the integration of 6G and federated learning and provide potential federated learning applications for 6G.  ...  Secure Federated Learning For 6G Due to the wide range of 6G network connections, FL will suffer malicious attacks from heterogeneous networks, heterogeneous devices, and malicious participants during  ... 
arXiv:2006.02931v2 fatcat:df3bzirq2fcpnp7h3kagdgamiy

From Federated to Fog Learning: Distributed Machine Learning over Heterogeneous Wireless Networks [article]

Seyyedali Hosseinalipour and Christopher G. Brinton and Vaneet Aggarwal and Huaiyu Dai and Mung Chiang
2020 arXiv   pre-print
There are several challenges with employing conventional federated learning in contemporary networks, due to the significant heterogeneity in compute and communication capabilities that exist across devices  ...  Fog learning enhances federated learning along three major dimensions: network, heterogeneity, and proximity.  ...  This hybrid learning paradigm will exploit the multi-layer structure of fog networks to optimize performance in the presence of heterogeneous network resources.  ... 
arXiv:2006.03594v3 fatcat:mpcav4qexvgwdmnvvr4qzuiblm

Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism [article]

Latif U. Khan, Shashi Raj Pandey, Nguyen H. Tran, Walid Saad, Zhu Han, Minh N. H. Nguyen, Choong Seon Hong
2020 arXiv   pre-print
Federated learning can be a promising solution for enabling IoT-based smart applications. In this paper, we present the primary design aspects for enabling federated learning at network edge.  ...  We model the incentive-based interaction between a global server and participating devices for federated learning via a Stackelberg game to motivate the participation of the devices in the federated learning  ...  The distributed federated optimization scheme of [10] allows us to tackle both system-level and statistical heterogeneity efficiently.  ... 
arXiv:1911.05642v3 fatcat:k55v2icilnblpcunxougmfjw54

Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges [article]

Latif U. Khan, Walid Saad, Zhu Han, Ekram Hossain, Choong Seon Hong
2021 arXiv   pre-print
Second, we devise a taxonomy for federated learning over IoT networks.  ...  In this paper, first, we present the recent advances of federated learning towards enabling federated learning-powered IoT applications.  ...  FedAvg has been used as a federated optimization scheme in FedHealth.  ... 
arXiv:2009.13012v2 fatcat:4oqifqi5czfyxiqe7gjewmuzsq

Federated Learning of Molecular Properties with Graph Neural Networks in a Heterogeneous Setting [article]

Wei Zhu, Jiebo Luo, Andrew White
2022 arXiv   pre-print
In this work, we introduce federated heterogeneous molecular learning to address these challenges.  ...  Another challenge is that different intuitions are interested in different classes of molecules, creating heterogeneous data that cannot be easily joined by conventional distributed training.  ...  Trained local models will heavily deviate from each other in this example, and it is thus sub-optimal to directly apply vanilla federated learning methods, e.g., Federated Average (FedAvg), to aggregate  ... 
arXiv:2109.07258v3 fatcat:e4dntvhf7jcsdmnbn67wum23xa

Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS [article]

Rui Song, Liguo Zhou, Venkatnarayanan Lakshminarasimhan, Andreas Festag, Alois Knoll
2022 arXiv   pre-print
In this paper, we introduce a federated learning framework coping with Hierarchical Heterogeneity (H2-Fed), which can notably enhance the conventional pre-trained deep learning model.  ...  The experiment results indicate that our method can well balance the learning accuracy and stability according to the knowledge of heterogeneity in current communication networks.  ...  To address the heterogeneity problems in C-ITS as analyzed in the previous Section III, we employ the method defined in (6) for federated optimization in hierarchical systems and propose a Federated Learning  ... 
arXiv:2204.00215v2 fatcat:srz4inw5drealilezvkg3i6lla

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
We conduct a focused survey of federated learning in conjunction with other learning algorithms.  ...  Following the emerging trends, we also discuss federated learning in the intersection with other learning paradigms, termed as federated x learning, where x includes multitask learning, meta-learning,  ...  Inspired by fair resource allocation in wireless networks, the q-fair federated learning (q-FFL) [12] proposes an optimization algorithm to ensure fair performance, i.e., a more uniform distribution  ... 
arXiv:2102.12920v2 fatcat:5fcwfhxibbedbcbuzrfyqdedky

A Survey of Federated Learning for Edge Computing: Research Problems and Solutions

Qi Xia, Winson Ye, Zeyi Tao, Jindi Wu, Qun Li
2021 High-Confidence Computing  
In this survey, we provide a new perspective on the applications, development tools, communication efficiency, security & privacy, migration and scheduling in edge federated learning.  ...  Federated Learning is a machine learning scheme in which a shared prediction model can be collaboratively learned by a number of distributed nodes using their locally stored data.  ...  System heterogeneity refers to the different hardwares (CPU, GPU, memory), network configurations, and power supplies of nodes in edge federated learning.  ... 
doi:10.1016/j.hcc.2021.100008 fatcat:fzzqredg6nfsxg6wlu5h7chixq

Review and Designs of Federated Management in Future Internet Architectures [chapter]

Martín Serrano, Steven Davy, Martin Johnsson, Willie Donnelly, Alex Galis
2011 Lecture Notes in Computer Science  
In this paper we discuss issues about federated management targeting information sharing capabilities for heterogeneous infrastructure.  ...  The Future Internet as a design conception is network and serviceaware addressing social and economic trends in a service oriented way.  ...  The work introduced in this paper is a contribution to SFI FAME-SRC (Federated, Autonomic Management of End-to-End Communications Services -Scientific Research Cluster).  ... 
doi:10.1007/978-3-642-20898-0_4 fatcat:3ptoeeldgfcr5odjjs4uvmaaxi

Connecting Distributed Pockets of EnergyFlexibility through Federated Computations:Limitations and Possibilities [article]

Javad Mohammadi, Jesse Thornburg
2020 arXiv   pre-print
In this paper, we first establish the need for federated computations to achieve energy optimization goals of the future power grid.  ...  Through federated computation, agents collaboratively solve learning and optimization problems while respecting each agent's privacy and overcoming barriers of cross-device and cross-organization data  ...  Federated computation enables large-scale machine learning and optimization across heterogeneous agents.  ... 
arXiv:2009.10182v1 fatcat:u7ny2p6u6faqvkkjavz4zo6bye

FedDANE: A Federated Newton-Type Method [article]

Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith
2020 arXiv   pre-print
In this work, we propose FedDANE, an optimization method that we adapt from DANE, a method for classical distributed optimization, to handle the practical constraints of federated learning.  ...  In particular, through empirical simulations on both synthetic and real-world datasets, FedDANE consistently underperforms baselines of FedAvg and FedProx in realistic federated settings.  ...  To handle heterogeneity and high communication costs in federated networks, a popular approach for federated optimization methods involves allowing for local updating and low participation [5] .  ... 
arXiv:2001.01920v1 fatcat:wcong6yerff2xa2zod2lilrlki
« Previous Showing results 1 — 15 out of 70,302 results