Developing a knowledge-guided federated graph attention learning network with a diffusion module to diagnose Alzheimer's disease

Xuegang Song, Kaixiang Shu, Peng Yang, Cheng Zhao, Feng Zhou, Alejandro F. Frangi, Jiuwen Cao, Xiaohua Xiao, Shuqiang Wang, Tianfu Wang, Baiying Lei

Abstract: Highlights•For AD intelligent diagnosis, we propose a knowledge-guided federated graph attention learning network, mainly including three contributions: 1) a knowledge-guided LassoNet was used to select and prioritize discriminative features; 2) an attention-guided diffusion module was used to synthesize samples; and 3) a federated graph attention learning net-work was used to learn deep features. Experimental results show that the proposed framework can achieve state-of-the-art performance.

External IDs:dblp:journals/mia/SongSYZZFCXWWL26