AutoDV: An End-to-End Deep Learning Model for High-Dimensional Data Visualization

High-dimensional data visualization (HDV) plays an important role in data science and engineering applications. Traditional HDV methods, such as Autoencoder and t-SNE, require hyper-parameter tuning and iterative optimization on every dataset and cannot effectively utilize the knowledge from historical low-dimension representation, which lowers the efficiency, convenience, and accuracy in real applications. In this paper, we present AutoDV, an end-to-end deep learning model, for high-dimensional data visualization. AutoDV is built upon a graph transformer network and an invariant loss function and is trained on a number of diverse datasets converted into multi-weight graphs. Given a new dataset, AutoDV outputs the 2D or 3D embeddings of all data points directly. AutoDV has the following merits: 1) There is no hyper-parameter selection during the data visualization stage; 2) The end-to-end model avoids re-training or iterative optimization when visualizing data; 3) The input dataset can have any number of features and can be from any domain. Our experiments show that AutoDV can successfully generalize to unseen datasets without retraining with 89.37% precision of t-SNE and 91.05% precision of UMAP on the unseen CIFAR10 datasets. Compared with existing parametric data visualization deep models, our method obtains a significant improvement with 86.65% precision gain. AutoDV can perform even better than t-SNE and UMAP on gene and UCI tabular datasets. The project is available at https://github.com/DryDew/AutoDV.