-
DeceFL: A Principled Decentralized Federated Learning Framework
DeceFL is a decentralized federated learning algorithm that eliminates the need for a central server and maintains convergence property. -
Hyperspectral pasture image dataset
Hyperspectral pasture image dataset with imbalanced class distributions and disparate volumes of data among different sites -
Federated Data Model
Medical image segmentation task using cardiac magnetic resonance images from different hospitals. -
XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning
User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and... -
UCI Bank Marketing Dataset (UBMD), Lesion Disease Classification (LDC) and CIF...
The authors used the UCI Bank Marketing Dataset (UBMD), Lesion Disease Classification (LDC) and CIFAR-10 datasets for their experiments. -
Light Federated and Continual Consensus (LFedCon2)
A federated and continual learning framework for classification tasks in a society of devices -
DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via...
The authors propose a general framework to solve the two challenges simultaneously: inter-client data heterogeneity and intra-client data noise. The framework uses... -
Federated Unlearning via Class-Discriminative Pruning
We explore the problem of selectively forgetting categories from trained CNN classification models in federated learning (FL). -
Delay Sensitive Hierarchical Federated Learning
The authors studied the impact of local averaging on the performance of federated learning systems in the presence of communication delay between the clients and the parameter... -
Ransomware Detection using Federated Learning based on CNN Model
The dataset is used for ransomware detection using a CNN model based on federated learning. -
Unsupervised Clustered Federated Learning in Complex Multi-source Acoustic En...
The dataset is a complex multi-source acoustic environment and an improved algorithm for the estimation of source-dominated microphone clusters in acoustic sensor networks. -
MNIST and CIFAR-10 datasets
The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions. -
On-demand Quantization for Green Federated Diffusion in Mobile Edge Networks
The dataset used in this paper is a federated diffusion model for mobile edge networks. -
FedNST: Federated Noisy Student Training for Automatic Speech Recognition
Federated Noisy Student Training for Automatic Speech Recognition -
An On-Device Federated Learning Approach for Cooperative Model Update between...
The proposed on-device federated learning approach is evaluated using three datasets: UAH-DriveSet, Smartphone HAR, and MNIST. -
Proposed Framework
The proposed framework aims to address the limitations of deep learning applications for ECG signal classification. Secondly, we proposed a new classifier for ECG signals. When... -
Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Bas...
Human Activity Recognition on mobile devices using a realistic heterogeneous setting with four different public datasets.
