Results 121 to 130 of about 34,864,804 (179)

Federated Learning With Non-IID Data: A Survey

IEEE Internet of Things Journal
Federated learning (FL) is an efficient decentralized machine learning methodology for processing nonindependent and identically distributed (non-IID) data due to geographical and temporal distribution differences.
Yueyue Dai, Yan Zhang, Heng Pan
exaly   +4 more sources

Federated Learning With Non-IID Data in Wireless Networks

IEEE Transactions on Wireless Communications, 2021
Federated learning provides a promising paradigm to enable network edge intelligence in the future sixth generation (6G) systems. However, due to the high dynamics of wireless circumstances and user behavior, the collected training data is non ...
Zhong-Yuan Zhao, Chen-Yuan Feng, Wei-Ming Hong, Jiamo Jiang, Chao Jia, Tony Q. S. Quek, M. Peng   +6 more
semanticscholar   +3 more sources

A Thorough Assessment of the Non-IID Data Impact in Federated Learning

Journal of Industrial Information Integration
Federated learning (FL) allows collaborative machine learning (ML) model training among decentralized clients'information, ensuring data privacy. The decentralized nature of FL deals with non-independent and identically distributed (non-IID) data.
Daniel Mauricio Jimenez Gutierrez, Mehrdad Hassanzadeh, Aris Anagnostopoulos, Ioannis Chatzigiannakis, Andrea Vitaletti   +4 more
semanticscholar   +6 more sources

Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions

arXiv.org
Recent advances in machine learning have highlighted Federated Learning (FL) as a promising approach that enables multiple distributed users (so-called clients) to collectively train ML models without sharing their private data.
Daniel Mauricio Jimenez Gutierrez, David Solans, Mikko A. Heikkilä, Andrea Vitaletti, Nicolas Kourtellis, Aris Anagnostopoulos, Ioannis Chatzigiannakis   +6 more
semanticscholar   +3 more sources

Joint User Association and Resource Allocation for Wireless Hierarchical Federated Learning With IID and Non-IID Data [PDF]

IEEE Transactions on Wireless Communications, 2022
In this work, hierarchical federated learning (HFL) over wireless multi-cell networks is proposed for large-scale model training while preserving data privacy. However, the imbalanced data distribution has a significant impact on the convergence rate and
Shengli Liu, Guanding Yu, Xianfu Chen
exaly   +2 more sources

A state-of-the-art survey on solving non-IID data in Federated Learning

Future Generation Computer Systems, 2022
Jia Zhu, Xiaodong Ma
exaly   +2 more sources

Optimizing Federated Learning on Non-IID Data with Reinforcement Learning

IEEE Conference on Computer Communications, 2020
The widespread deployment of machine learning applications in ubiquitous environments has sparked interests in exploiting the vast amount of data stored on mobile devices.
Hao Wang, Zakhary Kaplan, Di Niu, Bao-Chun Li   +3 more
semanticscholar   +1 more source

FedRS: Federated Learning with Restricted Softmax for Label Distribution Non-IID Data

Knowledge Discovery and Data Mining, 2021
Federated Learning (FL) aims to generate a global shared model via collaborating decentralized clients with privacy considerations. Unlike standard distributed optimization, FL takes multiple optimization steps on local clients and then aggregates the ...
Xin-Chun Li, De-Chuan Zhan
semanticscholar   +1 more source

Non-IIDness Learning in Behavioral and Social Data

The Computer Journal, 2013
Most of the classic theoretical systems and tools in statistics, data mining and machine learning are built on the fundamental assumption of IIDness, which assumes the independence and identical distribution of underlying objects, attributes and/or values.
openaire   +1 more source

Decentralized Federated Learning with Non-IID Data: Challenges, Trends, and Future Opportunities

ACM Computing Surveys
As artificial intelligence and machine learning advance, increasing privacy concerns and regulatory constraints have limited cross-border data sharing for traditional model training.
Wu-Chun Chung, Chao-Ai Lo, Yan-Hui Lin, Zhi-Hao Chen, Che-Lun Hung   +4 more
semanticscholar   +1 more source