Results 11 to 20 of about 1,704,441 (287)
Homophily outlier detection in non-IID categorical data [PDF]
Data Mining and Knowledge Discovery, 2021 To appear in Data Ming and Knowledge Discovery ...
Guansong Pang +2 more
openaire +3 more sources
Detecting Outliers in Non-IID Data: A Systematic Literature Review
IEEE Access, 2023 Outlier detection (outlier and anomaly are used interchangeably in this review) in non-independent and identically distributed (non-IID) data refers to identifying unusual or unexpected observations in datasets that do not follow an independent and ...
Shafaq Siddiqi +3 more
doaj +2 more sources
Fast converging Federated Learning with Non-IID Data
2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring), 2023 With the advancement of device capabilities, Internet of Things (IoT) devices can employ built-in hardware to perform machine learning (ML) tasks, extending their horizons in many promising directions. In traditional ML, data are sent to a server for training. However, this approach raises user privacy concerns.
Sigg Stephan, Naas Si-Ahmed
openaire +3 more sources
Data augmentation scheme for federated learning with non-IID data [PDF]
Tongxin xuebao, 2023 To solve the problem that the model accuracy remains low when the data are not independent and identically distributed (non-IID) across different clients in federated learning, a privacy-preserving data augmentation scheme was proposed.Firstly, a data ...
Lingtao TANG, Di WANG, Shengyun LIU
doaj +4 more sources
IEEE AccessFederated 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 +4 more
doaj +2 more sources
Entropy to Mitigate Non-IID Data Problem on Federated Learning for the Edge Intelligence Environment
IEEE Access, 2023 Machine Learning (ML) algorithms process input data making it possible to recognize and extract patterns from a large data volume. Likewise, Internet of Things (IoT) devices provide knowledge in a Federated Learning (FL) environment, sharing parameters ...
Fernanda C. Orlandi +4 more
doaj +2 more sources
Federated PAC-Bayesian Learning on Non-IID Data
ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023 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
Zihao Zhao 0001 +3 more
openaire +3 more sources
Addressing Non-IID with Data Quantity Skew in Federated Learning
InformationNon-IID is one of the key challenges in federated learning. Data heterogeneity may lead to slower convergence, reduced accuracy, and more training rounds.
Narisu Cha, Long Chang
doaj +2 more sources
Advanced Optimization Techniques for Federated Learning on Non-IID Data
Future InternetFederated learning enables model training on multiple clients locally, without the need to transfer their data to a central server, thus ensuring data privacy.
Filippos Efthymiadis +3 more
doaj +2 more sources
IEEE AccessIn sentiment analysis, data are commonly distributed across many devices, and traditional machine learning requires transferring these data to a central location exposing data to security and privacy risks. Federated Learning (FL) avoids this transfer by
Davoud Gholamiangonabadi +1 more
doaj +2 more sources