Results 251 to 260 of about 9,950,038 (297)

Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data

arXiv.org
Fine-tuning pre-trained models is a popular approach in machine learning for solving complex tasks with moderate data. However, fine-tuning the entire pre-trained model is ineffective in federated data scenarios where local data distributions are ...
Pei-Yau Weng, Minh Hoang, Lam M. Nguyen, My T. Thai, Tsui-Wei Weng, T. Hoang   +5 more
semanticscholar   +1 more source

Adaptive Client Clustering for Efficient Federated Learning Over Non-IID and Imbalanced Data

IEEE Transactions on Big Data
Federated learning (FL) is an emerging distributed and privacy-preserving machine learning framework. However, the performance of traditional FL methods is seriously impaired by the real-world data, which appear to be non-independent and identically ...
Biyao Gong, Tianzhang Xing, Zhidan Liu, Wei Xi, Xiaojiang Chen   +4 more
semanticscholar   +1 more source

BCE-FL: A Secure and Privacy-Preserving Federated Learning System for Device Fault Diagnosis Under Non-IID Condition in IIoT

IEEE Internet of Things Journal
Traditional device fault diagnostic methods in Industrial Internet of Things (IIoT) require nodes to upload local data to the cloud, which, however, may lead to privacy leakage issues.
Yiming Xiao, Haidong Shao, Jian Lin, Zhiqiang Huo, Bin Liu   +4 more
semanticscholar   +1 more source

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.
Zili Lu, Heng Pan, Yueyue Dai, Xueming Si, Yan Zhang   +4 more
semanticscholar   +1 more source

Long-Term Client Selection for Federated Learning With Non-IID Data: A Truthful Auction Approach

IEEE Internet of Things Journal
Federated learning (FL) provides a decentralized framework that enables universal model training through collaborative efforts on mobile nodes, such as smart vehicles in the Internet of Vehicles (IoV).
Jinghong Tan, Zhian Liu, Kun Guo, Mingxiong Zhao   +3 more
semanticscholar   +1 more source

Understanding Federated Learning from IID to Non-IID dataset: An Experimental Study

arXiv.org
As privacy concerns and data regulations grow, federated learning (FL) has emerged as a promising approach for training machine learning models across decentralized data sources without sharing raw data.
Jungwon Seo, Ferhat Ozgur Catak, Chunming Rong   +2 more
semanticscholar   +1 more source

FedSiam-DA: Dual-Aggregated Federated Learning via Siamese Network for Non-IID Data

IEEE Transactions on Mobile Computing
Federated learning (FL) is an effective mobile edge computing framework that enables multiple participants to collaboratively train intelligent models, without requiring large amounts of data transmission while protecting privacy.
Xin Wang, Yanhan Wang, Ming Yang, Feng Li, Xiaoming Wu, Lisheng Fan, Shibo He   +6 more
semanticscholar   +1 more source

Non-IID Federated Learning With Sharper Risk Bound

IEEE Transactions on Neural Networks and Learning Systems
In federated learning (FL), the not independently or identically distributed (non-IID) data partitioning impairs the performance of the global model, which is a severe problem to be solved. Despite the extensive literature related to the algorithmic novelties and optimization analysis of FL, there has been relatively little theoretical research devoted
Bojian Wei, Jian Li, Yong Liu, Weiping Wang   +3 more
openaire   +2 more sources

Correlated Differential Privacy for Non-IID Datasets

2017
Most previous work on differential privacy mainly focused on independent datasets, assuming that all records were sampled from a universe independently. However, in a real-world, many datasets contain strong coupling relations where some records are often correlated with each other.
Tianqing Zhu, Gang Li, Wanlei Zhou, Philip S. Yu   +3 more
openaire   +1 more source

Federated Learning With Adaptive Aggregation Weights for Non-IID Data in Edge Networks

IEEE Transactions on Cognitive Communications and Networking
Federated learning (FL) enables edge nodes to collaboratively train a global model under the coordination of a server without sharing local private data.
Xiaodong Li, Yulong Gao, Yansha Deng, Xinzhuo Jiang   +3 more
semanticscholar   +1 more source