Artificial Intelligence #federated learning#machine learning
Beyond Weights and Gradients: New Taxonomy Classifies Federated Learning Messages into Three Categories
A research paper by Guerrero, Vargas, Wang, Doan, and Nagels introduces a formal mathematical definition of a federated message and a taxonomy organizing exchanges into three categories: model structures, statistical summaries, and data-conditioned representations. The authors review 202 publications, noting a shift since 2021 toward diverse messaging paradigms beyond traditional weights and gradients, and evaluate trade-offs in computational demands, communication costs, and privacy risks.
Jun 16, 2026 1 source