TY - JOUR
T1 - PixelSNE
T2 - Pixel-Aligned Stochastic Neighbor Embedding for Efficient 2D Visualization with Screen-Resolution Precision
AU - Kim, Minjeong
AU - Choi, Minsuk
AU - Lee, Sunwoong
AU - Tang, Jian
AU - Park, Haesun
AU - Choo, Jaegul
PY - 2018/6/1
Y1 - 2018/6/1
N2 - Embedding and visualizing large-scale high-dimensional data in a two-dimensional space is an important problem, because such visualization can reveal deep insights of complex data. However, most of the existing embedding approaches run on an excessively high precision, even when users want to obtain a brief insight from a visualization of large-scale datasets, ignoring the fact that in the end, the outputs are embedded onto a fixed-range pixel-based screen space. Motivated by this observation and directly considering the properties of screen space in an embedding algorithm, we propose Pixel-Aligned Stochastic Neighbor Embedding (PixelSNE), a highly efficient screen resolution-driven 2D embedding method which accelerates Barnes-Hut tree-based t-distributed stochastic neighbor embedding (BH-SNE), which is known to be a state-of-the-art 2D embedding method. Our experimental results show a significantly faster running time for PixelSNE compared to BH-SNE for various datasets while maintaining comparable embedding quality.
AB - Embedding and visualizing large-scale high-dimensional data in a two-dimensional space is an important problem, because such visualization can reveal deep insights of complex data. However, most of the existing embedding approaches run on an excessively high precision, even when users want to obtain a brief insight from a visualization of large-scale datasets, ignoring the fact that in the end, the outputs are embedded onto a fixed-range pixel-based screen space. Motivated by this observation and directly considering the properties of screen space in an embedding algorithm, we propose Pixel-Aligned Stochastic Neighbor Embedding (PixelSNE), a highly efficient screen resolution-driven 2D embedding method which accelerates Barnes-Hut tree-based t-distributed stochastic neighbor embedding (BH-SNE), which is known to be a state-of-the-art 2D embedding method. Our experimental results show a significantly faster running time for PixelSNE compared to BH-SNE for various datasets while maintaining comparable embedding quality.
UR - http://www.scopus.com/inward/record.url?scp=85050260868&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85050260868&partnerID=8YFLogxK
U2 - 10.1111/cgf.13418
DO - 10.1111/cgf.13418
M3 - Article
AN - SCOPUS:85050260868
VL - 37
SP - 267
EP - 276
JO - Computer Graphics Forum
JF - Computer Graphics Forum
SN - 0167-7055
IS - 3
ER -