IEEE

FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models

Abstract: One-Shot Federated Learning (OSFL), a special decentralized machine learning paradigm, has recently gained significant attention. OSFL requires only a single round of client data or model ...
IEEE

Predictable Latent Features Learning for High-Dimensional Seasonal Time Series Analysis and Forecasting

Abstract: Analysis and prediction of high-dimensional time series are prevalent in numerous real-world scenarios, such as urban traffic. Traditional methods often struggle with the redundancy and ...