Graph convolutional network with sample and feature weights for Alzheimer’s disease diagnosis

作者：

Highlights：

• This paper considers the feature importance to solve the training set bias issue.

• This paper considers real-time interpretability on both samples and features.

• The data pre-processing method automatically selects clean samples in noisy dataset.

• Extensive experiments verify the effectiveness of the proposed method on AD datasets.

摘要

•This paper considers the feature importance to solve the training set bias issue.•This paper considers real-time interpretability on both samples and features.•The data pre-processing method automatically selects clean samples in noisy dataset.•Extensive experiments verify the effectiveness of the proposed method on AD datasets.

论文关键词：Alzheimer’s disease diagnosis,GCN,Training set bias,Interpretability

论文评审过程：Received 29 December 2021, Revised 12 April 2022, Accepted 19 April 2022, Available online 10 May 2022, Version of Record 10 May 2022.

论文官网地址：https://doi.org/10.1016/j.ipm.2022.102952