Alessandro Licciardi
PulseAugur coverage of Alessandro Licciardi — every cluster mentioning Alessandro Licciardi across labs, papers, and developer communities, ranked by signal.
-
New unsupervised framework detects malicious clients in federated learning
Researchers have developed WaSA, a novel unsupervised framework designed to detect malicious clients in federated learning environments. This system operates offline, before the main training process, by analyzing spect…
-
RIPPLE framework offers offline clustering for federated learning
Researchers have developed RIPPLE, a novel framework for clustered federated learning designed to address client drift in non-IID data scenarios. Unlike previous methods that integrate cluster discovery within the train…
-
New Federated Learning Algorithm Tackles Data Heterogeneity
Researchers have developed a novel client-selection algorithm for federated learning designed to mitigate issues arising from heterogeneous client data. This algorithm dynamically forms coalitions of clients based on th…