Figure 7
Visualize experimental results. The original data is from the test data of Alzheimer’s disease diagnosis task(AD-D) with few-feature settings. CN, MCI, and AD use purple, green, and yellow respectively. The first row is the result of using t-SNE to visualize the original data, and the second row is the result of using t-SNE to visualize the embeddings encoded by our model. Compared with the first row, the second row has obvious clustering effect. The columns from left to right are the visualize experimental results with a decreasing number of features, and the clustering effect becomes worse.
