Collaborative Distributed Machine Learning

Collaborative distributed machine learning (CDML) aims to train machine learning models across multiple decentralized devices while preserving data privacy. Current research focuses on improving the efficiency and robustness of CDML techniques, particularly federated learning and its variants like split learning, often adapting them for resource-constrained environments such as the Internet of Things (IoT). These advancements are significant for enabling large-scale model training with sensitive data, impacting fields ranging from healthcare to personalized recommendations.