Multi-site brain disease identification based on tensor decomposition and personalized federated learning

Chaojun Zhang, Jing Yang, Yuan Gao, Xiangli Yang, Shaojun Zou, Jieming Yang

Abstract: Highlights•A simple and effective multi-site brain disease recognition framework based on tensor decomposition and personalized federated learning is proposed to quickly integrate samples from different hospitals/sites while enabling personalized feature extraction at each site.•A designed Dynamic Prototype Aggregation (DPA) module utilizes a sliding window technique to capture the intrinsic characteristics of time-varying BOLD signals.•A dual-feature aggregation module is designed to aggregate coarse-grained shared features and fine-grained prototype representation features, respectively, to facilitate efficient knowledge sharing among sites.

External IDs:dblp:journals/nn/ZhangYGYZY26