Federated PAC-Bayesian Learning on Non-IID Data

Enhancing Human Activity Recognition with FedPA: Focusing on Non-IID Data Challenges in Federated Learning

X Wen, Y Wang, M Yuan, Y Geng, H Yu… - IEEE Sensors …, 2024 - ieeexplore.ieee.org
Federated learning (FL) revolutionizes distributed learning in human activity recognition
(HAR) by allowing clients to train models locally and share only model parameters, thus …
相关文章 所有 3 个版本
[PDF] arxiv.org

Can We Theoretically Quantify the Impacts of Local Updates on the Generalization Performance of Federated Learning?

P Ju, H Yang, J Liu, Y Liang, N Shroff - Proceedings of the Twenty-fifth …, 2024 - dl.acm.org
Federated Learning (FL) has gained significant popularity due to its effectiveness in training
machine learning models across diverse sites without requiring direct data sharing. While …
相关文章 所有 3 个版本

A Comparative Study of Clustering Distance Metrics for Personalized Federated Learning in Human Activity Recognition

X Wen, C Lu, R Hu, Y Geng, Y Wang… - 2024 International …, 2024 - ieeexplore.ieee.org
In Federated Learning (FL), Non-Independent and Identically Distributed (Non-IID) data
across different clients presents a significant challenge for a global model to effectively …
相关文章