Results 31 to 40 of about 109,032 (273)

Federated Learning with Non-IID Data

, 2018
Federated learning enables resource-constrained edge compute devices, such as mobile phones and IoT devices, to learn a shared model for prediction, while keeping the training data local. This decentralized approach to train models provides privacy, security, regulatory and economic benefits.
Zhao, Yue, Li, Meng, Lai, Liangzhen, Suda, Naveen, Civin, Damon, Chandra, Vikas   +5 more
openaire   +2 more sources

Ensemble Federated Adversarial Training with Non-IID data

, 2021
Despite federated learning endows distributed clients with a cooperative training mode under the premise of protecting data privacy and security, the clients are still vulnerable when encountering adversarial samples due to the lack of robustness.
Luo, Shuang, Zhu, Didi, Li, Zexi, Wu, Chao   +3 more
openaire   +2 more sources

Federated PAC-Bayesian Learning on Non-IID Data

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Existing research has either adapted the Probably Approximately Correct (PAC) Bayesian framework for federated learning (FL) or used information-theoretic PAC-Bayesian bounds while introducing their theorems, but few considering the non-IID challenges in FL. Our work presents the first non-vacuous federated PAC-Bayesian bound tailored for non-IID local
Zhao, Zihao, Liu, Yang, Ding, Wenbo, Zhang, Xiao-Ping   +3 more
openaire   +3 more sources

FedRDS: Federated Learning on Non-IID Data via Regularization and Data Sharing

Applied Sciences, 2023
Federated learning (FL) is an emerging decentralized machine learning framework enabling private global model training by collaboratively leveraging local client data without transferring it centrally.
Yankai Lv, Haiyan Ding, Hao Wu, Yiji Zhao, Lei Zhang   +4 more
doaj   +1 more source

Interictal Discharge Pattern in Preschool-Aged Children With Tuberous Sclerosis Complex Before and After Resective Epilepsy Surgery

Frontiers in Neurology, 2022
ObjectiveTo analyze the interictal discharge (IID) patterns on pre-operative scalp electroencephalogram (EEG) and compare the changes in IID patterns after removal of epileptogenic tubers in preschool children with tuberous sclerosis complex (TSC ...
Liu Yuan, Liu Yuan, Yangshuo Wang, Shuhua Cheng, Junchen Zhang, Shaohui Zhang, Tinghong Liu, Guojun Zhang, Guojun Zhang, Shuli Liang, Shuli Liang   +10 more
doaj   +1 more source

A Privacy-Preserving Collaborative Federated Learning Framework for Detecting Retinal Diseases

IEEE Access
The rapid advancement in technology has simplified human life and provides convenience. However, this convenience has led to many lifestyle diseases like diabetes and obesity.
Seema Gulati, Kalpna Guleria, Nitin Goyal, Ahmad Ali AlZubi, Angel Kuc Castilla   +4 more
doaj   +1 more source

A Collaborative Privacy Preserved Federated Learning Framework for Pneumonia Detection using Diverse Chest X-ray Data Silos [PDF]

International Journal of Mathematical, Engineering and Management Sciences
Pneumonia detection from chest X-rays remains one of the most challenging tasks in the traditional centralized framework due to the requirement of data consolidation at the central location raising data privacy and security concerns.
Shagun Sharma, Kalpna Guleria
doaj   +1 more source

FLY-SMOTE: Re-Balancing the Non-IID IoT Edge Devices Data in Federated Learning System

IEEE Access, 2022
In recent years, the data available from IoT devices have increased rapidly. Using a machine learning solution to detect faults in these devices requires the release of device data to a central server.
Raneen Younis, Marco Fisichella
doaj   +1 more source

Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data

, 2023
On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized.
Bennis, Mehdi, Jeong, Eunjeong, Kim, Hyesung, Kim, Seong-Lyun, Oh, Seungeun, Park, Jihong   +5 more
core  

Federated Conditional Variational Auto Encoders for Cyber Threat Intelligence: Tackling Non-IID Data in SDN Environments

IEEE Access
Federated Learning is a promising paradigm for sharing Cyber Threat Intelligence (CTI) without privacy issues by leveraging the cross-silos data in Software Defined Networking (SDN).
Syed Hussain Ali Kazmi, Rosilah Hassan, Faizan Qamar, Kashif Nisar, Mohammed Azmi Al-Betar   +4 more
doaj   +1 more source