Information retrieval approach to meta-visualization

Research output: Contribution to journal › Article › Scientific › peer-review

Standard

Information retrieval approach to meta-visualization. / Peltonen, Jaakko; Lin, Ziyuan.

In: Machine Learning, Vol. 99, No. 2, 01.05.2015, p. 189-229.

Research output: Contribution to journal › Article › Scientific › peer-review

Author

Peltonen, Jaakko ; Lin, Ziyuan. / Information retrieval approach to meta-visualization. In: Machine Learning. 2015 ; Vol. 99, No. 2. pp. 189-229.

Bibtex - Download

@article{5cb35d5f2f8d44728de5af6d9bbc141a,

title = "Information retrieval approach to meta-visualization",

abstract = "Visualization is crucial in the first steps of data analysis. In visual data exploration with scatter plots, no single plot is sufficient to analyze complicated high-dimensional data sets. Given numerous visualizations created with different features or methods, meta-visualization is needed to analyze the visualizations together. We solve how to arrange numerous visualizations onto a meta-visualization display, so that their similarities and differences can be analyzed. Visualization has recently been formalized as an information retrieval task; we extend this approach, and formalize meta-visualization as an information retrieval task whose performance can be rigorously quantified and optimized. We introduce a machine learning approach to optimize the meta-visualization, based on an information retrieval perspective: two visualizations are similar if the analyst would retrieve similar neighborhoods between data samples from either visualization. Based on the approach, we introduce a nonlinear embedding method for meta-visualization: it optimizes locations of visualizations on a display, so that visualizations giving similar information about data are close to each other. In experiments we show such meta-visualization outperforms alternatives, and yields insight into data in several case studies.",

keywords = "Meta-visualization, Neighbor embedding, Nonlinear dimensionality reduction",

author = "Jaakko Peltonen and Ziyuan Lin",

year = "2015",

month = "5",

day = "1",

doi = "10.1007/s10994-014-5464-x",

language = "English",

volume = "99",

pages = "189--229",

journal = "Machine Learning",

issn = "0885-6125",

publisher = "Springer Verlag",

number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Information retrieval approach to meta-visualization

AU - Peltonen, Jaakko

AU - Lin, Ziyuan

PY - 2015/5/1

Y1 - 2015/5/1

N2 - Visualization is crucial in the first steps of data analysis. In visual data exploration with scatter plots, no single plot is sufficient to analyze complicated high-dimensional data sets. Given numerous visualizations created with different features or methods, meta-visualization is needed to analyze the visualizations together. We solve how to arrange numerous visualizations onto a meta-visualization display, so that their similarities and differences can be analyzed. Visualization has recently been formalized as an information retrieval task; we extend this approach, and formalize meta-visualization as an information retrieval task whose performance can be rigorously quantified and optimized. We introduce a machine learning approach to optimize the meta-visualization, based on an information retrieval perspective: two visualizations are similar if the analyst would retrieve similar neighborhoods between data samples from either visualization. Based on the approach, we introduce a nonlinear embedding method for meta-visualization: it optimizes locations of visualizations on a display, so that visualizations giving similar information about data are close to each other. In experiments we show such meta-visualization outperforms alternatives, and yields insight into data in several case studies.

AB - Visualization is crucial in the first steps of data analysis. In visual data exploration with scatter plots, no single plot is sufficient to analyze complicated high-dimensional data sets. Given numerous visualizations created with different features or methods, meta-visualization is needed to analyze the visualizations together. We solve how to arrange numerous visualizations onto a meta-visualization display, so that their similarities and differences can be analyzed. Visualization has recently been formalized as an information retrieval task; we extend this approach, and formalize meta-visualization as an information retrieval task whose performance can be rigorously quantified and optimized. We introduce a machine learning approach to optimize the meta-visualization, based on an information retrieval perspective: two visualizations are similar if the analyst would retrieve similar neighborhoods between data samples from either visualization. Based on the approach, we introduce a nonlinear embedding method for meta-visualization: it optimizes locations of visualizations on a display, so that visualizations giving similar information about data are close to each other. In experiments we show such meta-visualization outperforms alternatives, and yields insight into data in several case studies.

KW - Meta-visualization

KW - Neighbor embedding

KW - Nonlinear dimensionality reduction

UR - http://www.scopus.com/inward/record.url?scp=84939887799&partnerID=8YFLogxK

U2 - 10.1007/s10994-014-5464-x

DO - 10.1007/s10994-014-5464-x

M3 - Article

VL - 99

SP - 189

EP - 229

JO - Machine Learning

JF - Machine Learning

SN - 0885-6125

IS - 2

ER -

TUTCRIS Research Portal