Tianchi Liao

Soft-consensual Federated Learning for Data Heterogeneity via Multiple Paths

Federated learning enables collaborative training while preserving the privacy of all participants. However, the heterogeneity in data distribution across multiple training nodes poses significant challenges to the construction of federated models. Prior studies were dedicated to mitigating the effects of data heteroge...

Learning in the Right Subspace: Personalized Differential Private Federated Learning with Noise Filtering

FedSPA, a Subspace Projection Aggregation personalized differential private Federated learning framework, is proposed, which not only effectively guides the aggregation of client personalized differential privacy but also reduces communication overhead.

Learning in the Right Subspace: Personalized Differential Private Federated Learning with Noise Filtering

Differential privacy (DP) mechanisms have been widely adopted in federated learning (FL) to enhance model security. However, existing approaches predominantly employ uniform privacy budgets, neglecting personalized requirements arising from heterogeneous user privacy preferences. Such uniform privacy configurations typ...

Dual prototypes for heterogeneous Federated Learning: A degradation perspective