B1425
Title: saVAE for nonlinear dimension reduction
Authors: Hyonho Chun - KAIST (Korea, South) [presenting]
Abstract: Deep generative models naturally become nonlinear dimension reduction tools to visualize large-scale datasets such as single-cell RNA sequencing datasets for revealing latent grouping patterns or identifying outliers. The variational autoencoder (VAE) is a popular deep generative method, equipped with encoder/decoder structures. The encoder and decoder are useful when a new sample is mapped to the latent space, and a data point is generated from a point in a latent space. However, the VAE does not show the grouping pattern clearly without additional annotation information. On the other hand, similarity-based dimension reduction methods such as t-SNE or UMAP present clear grouping patterns even though these methods do not have encoder/decoder structures. To bridge this gap, a new approach is proposed that adopts similarity information in the VAE framework. The method is able to produce clearer grouping patterns than those of other regularized VAE methods by utilizing similarity information encoded in the data via the highly celebrated UMAP loss function.
