Search papers, labs, and topics across Lattice.
Center for the Applied Statistics, School of Statistics, Renmin University of China
2
0
4
3
FedSEPT achieves superior local adaptation without sacrificing global generalization, even under stringent privacy conditions.
By intelligently perturbing class prototypes based on their discriminative power, VPDR achieves a superior privacy-utility trade-off in federated learning compared to naive Gaussian noise.
