Results 71 to 80 of about 34,864,804 (179)

Adaptive Federated Learning on Non-IID Data With Resource Constraint

, 2022
Federated learning (FL) has been widely recognized as a promising approach by enabling individual end-devices to cooperatively train a global model without exposing their own data.
Zhan, Yufeng, Zeng, Deze, Liu, Qifeng, Zhang, Jie, Guo, Song, Qu, Zhihao, Akerkar, Rajendra   +6 more
core   +1 more source

Communication Efficiency and Non-Independent and Identically Distributed Data Challenge in Federated Learning: A Systematic Mapping Study

Applied Sciences
Federated learning has emerged as a promising approach for collaborative model training across distributed devices. Federated learning faces challenges such as Non-Independent and Identically Distributed (non-IID) data and communication challenges.
Basmah Alotaibi, Fakhri Alam Khan, Sajjad Mahmood   +2 more
doaj   +1 more source

The Non-IID Data Quagmire of Decentralized Machine Learning

CoRR, 2019
Many large-scale machine learning (ML) applications need to perform decentralized learning over datasets generated at different devices and locations. Such datasets pose a significant challenge to decentralized learning because their different contexts result in significant data distribution skew across devices/locations.
Kevin Hsieh, Amar Phanishayee, Onur Mutlu, Phillip B. Gibbons   +3 more
openaire   +3 more sources

Cross-Gradient Aggregation for Decentralized Learning from Non-IID data [PDF]

, 2021
Decentralized learning enables a group of collaborative agents to learn models using a distributed dataset without the need for a central parameter server.
Esfandiari, Yasaman, Hegde, Chinmay, Tan, Sin Yong, Jiang, Zhanhong, Balu, Aditya, Herron, Ethan, Sarkar, Soumik   +6 more
core  

Federated Geometric Monte Carlo Clustering to Counter Non-IID Datasets [PDF]

, 2022
Federated learning allows clients to collaboratively train models on datasets that are acquired in different locations and that cannot be exchanged because of their size or regulations.
Marcus, Völp, Maria, Fernandes, Jérémie, Decouchant, Lydia, Chen, LUCCHETTI, Federico   +4 more
core   +1 more source

KL-FedDis: A federated learning approach with distribution information sharing using Kullback-Leibler divergence for non-IID data

Neuroscience Informatics
Data Heterogeneity or Non-IID (non-independent and identically distributed) data identification is one of the prominent challenges in Federated Learning (FL).
Md. Rahad, Ruhan Shabab, Mohd. Sultan Ahammad, Md. Mahfuz Reza, Amit Karmaker, Md. Abir Hossain   +5 more
doaj   +1 more source

Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data [PDF]

Computer Vision and Pattern Recognition
Federated learning achieves effective performance in modeling decentralized data. In practice, client data are not well-labeled, which makes it potential for federated unsupervised learning (FUSL) with non-IID data.
Xinting Liao, Weiming Liu, Chao-Chao Chen, Peng-Yang Zhou, Fengyuan Yu, Huabin Zhu, Binhui Yao, Tao Wang, Xiao-Lin Zheng, Yan-Chao Tan   +9 more
semanticscholar   +1 more source

Pretraining Client Selection Algorithm Based on a Data Distribution Evaluation Model in Federated Learning

IEEE Access
Federated Learning (FL) allows task initiators (servers) to utilize data from task participants (clients) to train machine learning models while protecting data privacy.
Chang Xu, Hong Liu, Kexin Li, Wanglei Feng, Wei Qi   +4 more
doaj   +1 more source

One-Shot Sequential Federated Learning for Non-IID Data by Enhancing Local Model Diversity [PDF]

ACM Multimedia
Traditional federated learning mainly focuses on parallel settings (PFL), which can suffer significant communication and computation costs. In contrast, one-shot and sequential federated learning (SFL) have emerged as innovative paradigms to alleviate ...
Nai-Bo Wang, Yuchen Deng, Wen-Jie Feng, Shi-Chen Fan, Jianwei Yin, See-Kiong Ng   +5 more
semanticscholar   +1 more source

Cloud–Edge–End Collaborative Federated Learning: Enhancing Model Accuracy and Privacy in Non-IID Environments

Sensors
Cloud–edge–end computing architecture is crucial for large-scale edge data processing and analysis. However, the diversity of terminal nodes and task complexity in this architecture often result in non-independent and identically distributed (non-IID ...
Ling Li, Lidong Zhu, Weibang Li
doaj   +1 more source