Federated learning (FL) enables a collaborative environment for training machine learning
models without sharing training data between users. This is typically achieved by …

In the field of heterogeneous federated learning (FL), the key challenge is to efficiently and
collaboratively train models across multiple clients with different data distributions, model …

Federated learning (FL) enables collaborative and privacy-preserving training of machine
learning (ML) models on federated data. However, the barriers to using FL are still high …

The divergence of Artificial Intelligence (AI) with Next-Generation (xG) mobile networks is
inevitable as it is driven by the demand for more intelligent mobile networks that can …

This study aims to investigate the intricate connections between physical fitness, cognitive
performance, and emotional well-being among senior high school students. The objective is …

This article highlights the features of using interactive boards in higher education institutions.
The expediency of incorporating interactive boards into the educational process is …

This is a B-mode project carried out under an employment contract with the company
Capgemini. In the recent years, it has been observed that clients are increasingly drawn to …

Machine learning (ML) technologies are rapidly advancing and being widely adopted for
various applications. Unlike traditional model training, which needs to store all user data in …

Abstract Decentralized Federated Learning (DFL) allows collaborative model training while
preserving data privacy, but it is vulnerable to poisoning attacks. This thesis proposes …

Klassisches maschinelles Lernen (ML) hat mehrere kritische Nachteile. Dazu gehören einen
zentralen Ausfallspunkt, wenig Datenprivatsphäre und einen Mehraufwand bei der …