About: GPU-Embedding of kNN-Graph Representing Large and High-Dimensional Data

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: GPU-Embedding of kNN-Graph Representing Large and High-Dimensional Data Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	GPU-Embedding of kNN-Graph Representing Large and High-Dimensional Data
Creator	Dzwinel, Witold Minch, Bartosz Nowak, Mateusz Wcisło, Rafał
Source	PMC
abstract	Interactive visual exploration of large and multidimensional data still needs more efficient [Formula: see text] data embedding (DE) algorithms. We claim that the visualization of very high-dimensional data is equivalent to the problem of 2D embedding of undirected kNN-graphs. We demonstrate that high quality embeddings can be produced with minimal time&memory complexity. A very efficient GPU version of IVHD (interactive visualization of high-dimensional data) algorithm is presented, and we compare it to the state-of-the-art GPU-implemented DE methods: BH-SNE-CUDA and AtSNE-CUDA. We show that memory and time requirements for IVHD-CUDA are radically lower than those for the baseline codes. For example, IVHD-CUDA is almost 30 times faster in embedding (without the procedure of kNN graph generation, which is the same for all the methods) of the largest ([Formula: see text]) YAHOO dataset than AtSNE-CUDA. We conclude that in the expense of minor deterioration of embedding quality, compared to the baseline algorithms, IVHD well preserves the main structural properties of ND data in 2D for radically lower computational budget. Thus, our method can be a good candidate for a truly big data ([Formula: see text]) interactive visualization.
has issue date	2020-06-15(xsd:dateTime)
bibo:doi	10.1007/978-3-030-50417-5_24
has license	no-cc
sha1sum (hex)	6de5c85573ee532bbb68836851d392469323c260
schema:url	https://doi.org/10.1007/978-3-030-50417-5_24
resource representing a document's title	GPU-Embedding of kNN-Graph Representing Large and High-Dimensional Data
has PubMed Central identifier	PMC7302810
schema:publication	Computational Science - ICCS 2020
resource representing a document's body	covid:6de5c85573ee532bbb68836851d392469323c260#body_text
is schema:about of	named entity 'memory' named entity 'interactive visualization' named entity 'memory' named entity 'baseline' named entity 'data' named entity 'time' named entity 'MINOR' named entity 'MEMORY' named entity 'GRAPH GENERATION' named entity 'EXAMPLE' named entity 'YAHOO' named entity 'SNE' named entity 'COMPUTATIONAL' named entity 'VISUAL' named entity 'IMPLEMENTED' named entity 'LARGEST' named entity 'LARGE' named entity 'CLAIM' named entity 'METHODS' named entity 'ALGORITHMS' named entity 'TIMES' named entity 'CONCLUDE' named entity 'QUALITY' named entity 'high-dimensional' named entity 'kNN' named entity 'high' named entity 'efficient' named entity 'candidate' named entity 'embedding' named entity 'compare' named entity 'kNN' named entity 'GPU' named entity 'multidimensional data' named entity 'High-Dimensional Data' named entity 'GPU' named entity 't-SNE' named entity 'GPU' named entity 'kNN' named entity 'lossy compression' named entity 'loss function' named entity 'graph' named entity 'floating point' named entity 'GPU' named entity 'CUDA' named entity 'force-directed' named entity '95%' named entity 'RMSprop' named entity 'kNNs' named entity 'kNN' named entity 'Euclidean distances' named entity 'high-dimensional data' named entity 'algorithmic complexity' named entity 'GDDR5' named entity 'loss function' named entity 'graph' named entity 'data mining' named entity 't-SNE' named entity 't-SNE' named entity 'approximately equal' named entity 'histograms' named entity 'probability' named entity 'time complexity' named entity 'histograms' named entity 'topological properties' named entity 'graph' named entity 'CUDA' named entity 'GPU' named entity 'remote server' named entity 'algorithm' named entity 'connected component' named entity 'Gaussian' named entity 'pseudo-code' named entity 'loss function' named entity 'GPU' named entity 'CUDA' named entity 'loss function' named entity 'N-dimensional' named entity 'CUDA' named entity 'KL divergence' named entity 'data science'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software