The Grassmannian Atlas: A General Framework for Exploring Linear Projections of High-Dimensional Data
Abstract
Linear projections are one of the most common approaches to visualize high-dimensional data. Since the space of possible projections is large, existing systems usually select a small set of interesting projections by ranking a large set of candidate projections based on a chosen quality measure. However, while highly ranked projections can be informative, some lower ranked ones could offer important complementary information. Therefore, selection based on ranking may miss projections that are important to provide a global picture of the data. Here, the proposed work fills this gap by presenting the Grassmannian Atlas, a framework that captures the global structures of quality measures in the space of all projections, which enables a systematic exploration of many complementary projections and provides new insights into the properties of existing quality measures.
- Authors:
-
- Univ. of Utah, Salt Lake City, UT (United States). Scientific Computing and Imaging Inst.
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- Tulane Univ., New Orleans, LA (United States). Dept. of Computer Science
- Publication Date:
- Research Org.:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE; National Science Foundation (NSF)
- OSTI Identifier:
- 1417962
- Report Number(s):
- LLNL-JRNL-733805
Journal ID: ISSN 0167-7055
- Grant/Contract Number:
- AC52-07NA27344; EE0004449; NA0002375; SC0007446; SC0010498
- Resource Type:
- Journal Article: Accepted Manuscript
- Journal Name:
- Computer Graphics Forum
- Additional Journal Information:
- Journal Volume: 35; Journal Issue: 3; Journal ID: ISSN 0167-7055
- Publisher:
- Wiley
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; Computer Graphics; Picture/Image Generation; Line and curve generation
Citation Formats
Liu, S., Bremer, P. -T, Jayaraman, J. J., Wang, B., Summa, B., and Pascucci, V. The Grassmannian Atlas: A General Framework for Exploring Linear Projections of High-Dimensional Data. United States: N. p., 2016.
Web. doi:10.1111/cgf.12876.
Liu, S., Bremer, P. -T, Jayaraman, J. J., Wang, B., Summa, B., & Pascucci, V. The Grassmannian Atlas: A General Framework for Exploring Linear Projections of High-Dimensional Data. United States. https://doi.org/10.1111/cgf.12876
Liu, S., Bremer, P. -T, Jayaraman, J. J., Wang, B., Summa, B., and Pascucci, V. 2016.
"The Grassmannian Atlas: A General Framework for Exploring Linear Projections of High-Dimensional Data". United States. https://doi.org/10.1111/cgf.12876. https://www.osti.gov/servlets/purl/1417962.
@article{osti_1417962,
title = {The Grassmannian Atlas: A General Framework for Exploring Linear Projections of High-Dimensional Data},
author = {Liu, S. and Bremer, P. -T and Jayaraman, J. J. and Wang, B. and Summa, B. and Pascucci, V.},
abstractNote = {Linear projections are one of the most common approaches to visualize high-dimensional data. Since the space of possible projections is large, existing systems usually select a small set of interesting projections by ranking a large set of candidate projections based on a chosen quality measure. However, while highly ranked projections can be informative, some lower ranked ones could offer important complementary information. Therefore, selection based on ranking may miss projections that are important to provide a global picture of the data. Here, the proposed work fills this gap by presenting the Grassmannian Atlas, a framework that captures the global structures of quality measures in the space of all projections, which enables a systematic exploration of many complementary projections and provides new insights into the properties of existing quality measures.},
doi = {10.1111/cgf.12876},
url = {https://www.osti.gov/biblio/1417962},
journal = {Computer Graphics Forum},
issn = {0167-7055},
number = 3,
volume = 35,
place = {United States},
year = {Sat Jun 04 00:00:00 EDT 2016},
month = {Sat Jun 04 00:00:00 EDT 2016}
}
Web of Science
Works referenced in this record:
Data Visualization With Multidimensional Scaling
journal, June 2008
- Buja, Andreas; Swayne, Deborah F.; Littman, Michael L.
- Journal of Computational and Graphical Statistics, Vol. 17, Issue 2
Coordinating Computational and Visual Approaches for Interactive Feature Selection and Multivariate Clustering
journal, December 2003
- Guo, Diansheng
- Information Visualization, Vol. 2, Issue 4
Visual Exploration of High Dimensional Scalar Functions
journal, November 2010
- Gerber, S.; Bremer, P.; Pascucci, V.
- IEEE Transactions on Visualization and Computer Graphics, Vol. 16, Issue 6
Optimal Sets of Projections of High-Dimensional Data
journal, January 2016
- Lehmann, Dirk J.; Theisel, Holger
- IEEE Transactions on Visualization and Computer Graphics, Vol. 22, Issue 1
GGobi: evolving from XGobi into an extensible framework for interactive data visualization
journal, August 2003
- Swayne, Deborah F.; Lang, Duncan Temple; Buja, Andreas
- Computational Statistics & Data Analysis, Vol. 43, Issue 4
Visualizing the quality of dimensionality reduction
journal, July 2013
- Mokbel, Bassam; Lueks, Wouter; Gisbrecht, Andrej
- Neurocomputing, Vol. 112
Subspace search and visualization to make sense of alternative clusterings in high-dimensional data
conference, October 2012
- Tatu, Andrada; Maas, Fabian; Farber, Ines
- 2012 IEEE Conference on Visual Analytics Science and Technology (VAST)
A Rank-by-Feature Framework for Interactive Exploration of Multidimensional Data
journal, April 2005
- Seo, Jinwook; Shneiderman, Ben
- Information Visualization, Vol. 4, Issue 2
Entropy-based subspace clustering for mining numerical data
conference, January 1999
- Cheng, Chun-Hung; Fu, Ada Waichee; Zhang, Yi
- Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '99
Subspace Clustering
journal, March 2011
- Vidal, Rene
- IEEE Signal Processing Magazine, Vol. 28, Issue 2
High-Dimensional Visual Analytics: Interactive Exploration Guided by Pairwise Views of Point Distributions
journal, November 2006
- Wilkinson, L.; Anand, A.; Grossman, R.
- IEEE Transactions on Visualization and Computer Graphics, Vol. 12, Issue 6
Multivariate volume visualization through dynamic projections
conference, November 2014
- Liu, Shusen; Wang, Bei; Thiagarajan, Jayaraman J.
- 2014 IEEE 4th Symposium on Large Data Analysis and Visualization (LDAV)
Topological Spines: A Structure-preserving Visual Representation of Scalar Fields
journal, December 2011
- Correa, C.; Lindstrom, P.; Bremer, Peer-Timo
- IEEE Transactions on Visualization and Computer Graphics, Vol. 17, Issue 12
Projection Pursuit Indexes Based on Orthonormal Function Expansions
journal, September 1993
- Cook, Dianne; Buja, Andreas; Cabrera, Javier
- Journal of Computational and Graphical Statistics, Vol. 2, Issue 3
Projection Pursuit for Exploratory Supervised Classification
journal, December 2005
- Lee, Eun-Kyung; Cook, Dianne; Klinke, Sigbert
- Journal of Computational and Graphical Statistics, Vol. 14, Issue 4
Quality Metrics in High-Dimensional Data Visualization: An Overview and Systematization
journal, December 2011
- Bertini, E.; Tatu, Andrada; Keim, Daniel
- IEEE Transactions on Visualization and Computer Graphics, Vol. 17, Issue 12
Distortion-Guided Structure-Driven Interactive Exploration of High-Dimensional Data: Interactive Data Exploration
journal, June 2014
- Liu, S.; Wang, B.; Bremer, P. -T.
- Computer Graphics Forum, Vol. 33, Issue 3
Works referencing / citing this record:
Frontier of Information Visualization and Visual Analytics in 2016
journal, May 2017
- Lu, Min; Chen, Siming; Lai, Chufan
- Journal of Visualization, Vol. 20, Issue 4
Recent research advances on interactive machine learning
journal, November 2018
- Jiang, Liu; Liu, Shixia; Chen, Changjian
- Journal of Visualization, Vol. 22, Issue 2
Recent Research Advances on Interactive Machine Learning
preprint, January 2018
- Jiang, Liu; Liu, Shixia; Chen, Changjian
- arXiv