XUEBIN MA

Experienced Associate Professor and Researcher specializing in Privacy-Preserving. Well-versed in differential privacy and federated machine learning. Seeking opportunities to further development and research on technological advancements.

AdaDP-CFL, It achieves model personalization and facilitates knowledge sharing among different groups through clustering and regularization techniques. Subsequently, the algorithm addresses the issue of adaptive clipping for various clients, formulated as a Markov decision process, by utilizing a deep deterministic policy gradient model based on gradient differences across client groups.

DP-CUDA, It first searches for domain-invariant features between the source and target domains and then transfers knowledge. Specifically, the model is trained in the source domain by supervised learning from labeled data. During the target model's training, feature learning is directly used end-to-end using unlabeled data, and differentially private noise is injected into the gradients.

• Association for Computing Machinery