Yan Sun

Tenghao Deng, Yan Sun

In recent years, with the continuous advancement of deep learning and the emergence of large-scale human motion datasets, human motion prediction technology has gradually gained prominence in various fields such as human-computer interaction, autonomous driving, sports analysis, and personnel tracking. This article introduces common model architectures in this domain along with their respective advantages and disadvantages. It also systematically summarizes recent research innovations, focusing on in-depth discussions of relevant papers in these areas, thereby highlighting forward-looking insights into the field's development. Furthermore, this paper provides a comprehensive overview of existing methods, commonly used datasets, and evaluation metrics in this field. Finally, it discusses some of the current limitations in the field and proposes potential future research directions to address these challenges and promote further advancements in human motion prediction.

Yifan Shi, Yingqi Liu, Yan Sun et al.

Personalized federated learning (PFL) aims to produce the greatest personalized model for each client to face an insurmountable problem--data heterogeneity in real FL systems. However, almost all existing works have to face large communication burdens and the risk of disruption if the central server fails. Only limited efforts have been used in a decentralized way but still suffers from inferior representation ability due to sharing the full model with its neighbors. Therefore, in this paper, we propose a personalized FL framework with a decentralized partial model training called DFedAlt. It personalizes the "right" components in the modern deep models by alternately updating the shared and personal parameters to train partially personalized models in a peer-to-peer manner. To further promote the shared parameters aggregation process, we propose DFedSalt integrating the local Sharpness Aware Minimization (SAM) optimizer to update the shared parameters. It adds proper perturbation in the direction of the gradient to overcome the shared model inconsistency across clients. Theoretically, we provide convergence analysis of both algorithms in the general non-convex setting for decentralized partial model training in PFL. Our experiments on several real-world data with various data partition settings demonstrate that (i) decentralized training is more suitable for partial personalization, which results in state-of-the-art (SOTA) accuracy compared with the SOTA PFL baselines; (ii) the shared parameters with proper perturbation make partial personalized FL more suitable for decentralized training, where DFedSalt achieves most competitive performance.