Tag: non-IID data

Researchers have developed FedHybrid-ViT, a privacy-preserving framework that fuses convolutional and transformer models within federated learning to detect deepfakes across ...

Researchers have developed FedML-DKD, a federated learning framework that uses Earth Mover's Distance to adaptively balance knowledge distillation and meta-learning, ...

Researchers in India have developed ASHA, a federated learning algorithm that weights each client's updates by a dynamic contribution score, ...

A new open-source simulator called FLInterrupt makes sudden client dropouts a controllable experimental variable in federated learning research, revealing how ...

A new federated learning framework called FedCAMP-IDS detects known and zero-day cyberattacks across heterogeneous IoT networks with up to 99.16 ...

Researchers have developed FedDeepRiskNet++, a federated learning framework that combines differential privacy, homomorphic encryption and adaptive scheduling to let hospitals ...

A new phased client selection method for federated learning improves accuracy, cuts training time and communication costs, and strengthens defenses ...

A new federated learning framework lets hospitals train chest X-ray diagnostic AI collaboratively without sharing patient data, and it outperforms ...

Researchers have built a federated hybrid quantum-classical neural network that classifies Alzheimer's disease from MRI scans with benchmark accuracies above ...

Researchers at Vanderbilt University have developed a resilient adaptive aggregation method that enables peer-to-peer machine learning networks to reach consensus ...