Giancarlo Fortino

Novel aggregation techniques for Memory Augmented Autoencoders in Federated Learning can enhance anomaly detection performance, even in shallow models.

Quantization is not just a compression technique; it fundamentally reshapes the performance and robustness of Federated Learning systems.

Resource-constrained smart meters can achieve competitive energy theft detection accuracy while preserving user privacy, thanks to a federated learning approach with differential privacy.