The paradigm of Differentially Private SGD~(DP-SGD) can provide a theoretical guarantee
for training data in both centralized and federated settings. However, the utility degradation …

Federated learning, as an emerging technology in the field of artificial intelligence,
effectively addresses the issue of data islands while ensuring privacy protection. However …

Single-cell RNA sequencing (scRNA-seq) is important to transcriptomic analysis of gene
expression. Recently, deep learning has facilitated the analysis of high-dimensional single …

In the era of Big Data, deep learning techniques provide intelligent solutions for various
problems in real-life scenarios. However, deep neural networks depend on large-scale …

Federated Learning (FL) trains a black-box and highdimensional model among different
clients by exchanging parameters instead of direct data sharing, which mitigates the privacy …