2017/12/25 by George C. Linderman, Manas Rachh, Jeremy G. Hoskins +2 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Algorithm #Artificial intelligence #Computation #Computer science #Convolution (computer science) #Dimensionality reduction #Embedding #Fast Fourier transform #Gene Regulatory Network Analysis #Gene expression and cancer classification #Interpolation (computer graphics) #Parallel computing #Single-cell and spatial transcriptomics #Visualization #cs.LG #stat.ML
paper · pdf · doi:10.1038/s41592-018-0308-4
arxiv created 2017/12/25 · openalex publication_date 2019/02/11 · arxiv updated 2019/02/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
t-distributed Stochastic Neighborhood Embedding (t-SNE) is a method for dimensionality reduction and visualization that has become widely popular in recent years. Efficient implementations of t-SNE are available, but they scale poorly to datasets with hundreds of thousands to millions of high dimensional data-points. We present Fast Fourier Transform-accelerated Interpolation-based t-SNE (FIt-SNE), which dramatically accelerates the computation of t-SNE. The most time-consuming step of t-SNE is a convolution that we accelerate by interpolating onto an equispaced grid and subsequently using the fast Fourier transform to perform the convolution. We also optimize the computation of input similarities in high dimensions using multi-threaded approximate nearest neighbors. We further present a modification to t-SNE called "late exaggeration," which allows for easier identification of clusters in t-SNE embeddings. Finally, for datasets that cannot be loaded into the memory, we present out-of-core randomized principal component analysis (oocPCA), so that the top principal components of a dataset can be computed without ever fully loading the matrix, hence allowing for t-SNE of large datasets to be computed on resource-limited machines.