Federated learning (FL) has been gaining attention for its ability to share knowledge while
maintaining user data, protecting privacy, increasing learning efficiency, and reducing …

Extensive research is underway to meet the hyperconnectivity demands of 6G networks,
driven by applications like XR/VR and holographic communications, which generate …

In this article we carry out a comparison between early (feature) and late (score) multimodal
fusion, for the two-class problem. The comparison is made first from a general perspective …

While machine learning (ML) research has recently grown more in popularity, its application
in the omics domain is constrained by access to sufficiently large, high-quality datasets …

This paper introduces FedSecurity, an end-to-end benchmark that serves as a
supplementary component of the FedML library for simulating adversarial attacks and …

Federated Domain Generalization (FDG) aims to train a global model that generalizes well
to new clients in a privacy-conscious manner, even when domain shifts are encountered …

Secure aggregation, which is a core component of federated learning, aggregates locally
trained models from distributed users at a central server. The “secure” nature of such …

In this work, we study practical heuristics to improve the performance of prefix-tree based
algorithms for differentially private heavy hitter detection. Our model assumes each user has …

Federated Learning (FL) is a machine learning technique that enables multiple entities to
collaboratively learn a shared model without exchanging their local data. Over the past …

This paper considers the secure aggregation problem for federated learning under an
information theoretic cryptographic formulation, where distributed training nodes (referred to …