Results 81 to 90 of about 31,140,578 (184)
Adversarially-Regularized Mixed Effects Deep Learning (ARMED) Models Improve Interpretability, Performance, and Generalization on Clustered (non-iid) Data. [PDF]
IEEE Trans Pattern Anal Mach Intell, 2023 Nguyen KP, Treacher AH, Montillo AA.
europepmc +1 more source
Federated Loss Exploration for Improved Convergence on Non-IID Data
Internò C, Olhofer M, Jin Y, Hammer B. Federated Loss Exploration for Improved Convergence on Non-IID Data. In: 2024 International Joint Conference on Neural Networks (IJCNN). IEEE International Joint Conference on Neural Networks (IJCNN).
Hammer, Barbara ; https://orcid.org/ +3 more
core +1 more source
CHPFL: Clustered adaptive hierarchical federated learning for edge-level personalization
High-Confidence ComputingFederated learning faces challenges with non-IID data distributions, often resulting in suboptimal performance for individual clients with the global model. To address this issue, we propose a clustered hierarchical personalized federated learning (CHPFL)
Lihua Song +4 more
doaj +1 more source
IEEE AccessDistributed denial of service (DDoS) is an awful cyber threat, becoming more prevalent with mature heterogeneous IoT (HetIoT) applications like intelligent agriculture, wearables, and self-driving cars. Developing intelligent intrusion detection systems (
Shalaka S. Mahadik +2 more
doaj +1 more source
Results in EngineeringThe advancement of autonomous vehicle technology relies heavily on sophisticated machine-learning models that facilitate real-time object detection and classification.
K. Vinoth, P. Sasikumar
doaj +1 more source
Federated Learning for Breast Cancer Classification: A Comparative Study of Aggregation Methods
InformationFederated Learning (FL) allows healthcare institutions to collaboratively develop machine learning models while safeguarding patient data, making it ideal for privacy-sensitive medical imaging.
Nadjat Saàdia Lachemi +2 more
doaj +1 more source
Differentially Private Federated Clustering Over Non-IID Data
IEEE Internet of Things Journal34 pages, 4 figures, 1 ...
Yiwei Li 0003 +3 more
openaire +2 more sources
Weighted Ensemble Distillation in Federated Learning with Non-IID Data
, 2022 Federated distillation (FD) is a novel algorithmic idea for federated learning (FL) that allows clients to use heterogeneous model architectures. This is achieved by distilling aggregated local model predictions on an unlabeled auxiliary dataset into ...
Eriksson, Oscar
core
A thorough assessment of the non-IID data impact in federated learning
Journal of Industrial Information IntegrationFederated learning (FL) allows collaborative machine learning (ML) model training among decentralized clients' information, ensuring data privacy. The decentralized nature of FL deals with non-independent and identically distributed (non-IID) data. This open problem has notable consequences, such as decreased model performance and more significant ...
Daniel Mauricio Jimenez Gutierrez +4 more
openaire +5 more sources
Analyzing the Impact of Non-IID Data on IoT-Enabled Federated Learning for ECG Arrhythmia Detection
The integration of Federated Learning (FL) in the Internet of Medical Things (IoMT) represents a cutting-edge solution, enabling the training of Artificial Intelligence (AI) models directly on edge devices without the need to share sensitive patient ...
Massimo De Vittorio +6 more
core +1 more source