Say we would like to use Graph Convolutional Networks for some link prediction task that involves biological/biomedical networks. Is the degree-normalized adjacency matrix (as commonly utilized in the literature) the best convolution matrix we can use for this purpose?

It's time to stop making t-SNE & UMAP plots. In a new preprint w/ Tara Chari we show that while they display some correlation with the underlying high-dimension data, they don't preserve local or global structure & are misleading. They're also arbitrary.🧵biorxiv.org/content/10.110…