Deepeye

towards automatic data visualization

Yuyu Luo, Xuedi Qin, Nan Tang, Guoliang Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Data visualization is invaluable for explaining the significance of data to people who are visually oriented. The central task of automatic data visualization is, given a dataset, to visualize its compelling stories by transforming the data (e.g., selecting attributes, grouping and binning values) and deciding the right type of visualization (e.g., bar or line charts). We present DEEPEYE, a novel system for automatic data visualization that tackles three problems: (1) Visualization recognition: given a visualization, is it 'good or 'bad'? (2) Visualization ranking: given two visualizations, which one is 'better'? And (3) Visualization selection: given a dataset, how to find top-k visualizations? DEEPEYE addresses (1) by training a binary classifier to decide whether a particular visualization is good or bad. It solves (2) from two perspectives: (i) Machine learning: it uses a supervised learning-To-rank model to rank visualizations; and (ii) Expert rules: it relies on experts' knowledge to specify partial orders as rules. Moreover, a 'boring' dataset may become interesting after data transformations (e.g., binning and grouping), which forms a large search space. We also discuss optimizations to efficiently compute top-k visualizations, for approaching (3). Extensive experiments verify the effectiveness of DEEPEYE.

Original languageEnglish
Title of host publicationProceedings - IEEE 34th International Conference on Data Engineering, ICDE 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages101-112
Number of pages12
ISBN (Electronic)9781538655207
DOIs
Publication statusPublished - 24 Oct 2018
Event34th IEEE International Conference on Data Engineering, ICDE 2018 - Paris, France
Duration: 16 Apr 201819 Apr 2018

Other

Other34th IEEE International Conference on Data Engineering, ICDE 2018
CountryFrance
CityParis
Period16/4/1819/4/18

Fingerprint

Data visualization
Visualization
Boring
Supervised learning
Learning systems
Classifiers

Keywords

  • Automatic
  • data visualization

ASJC Scopus subject areas

  • Information Systems
  • Information Systems and Management
  • Hardware and Architecture

Cite this

Luo, Y., Qin, X., Tang, N., & Li, G. (2018). Deepeye: towards automatic data visualization. In Proceedings - IEEE 34th International Conference on Data Engineering, ICDE 2018 (pp. 101-112). [8509240] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDE.2018.00019

Deepeye : towards automatic data visualization. / Luo, Yuyu; Qin, Xuedi; Tang, Nan; Li, Guoliang.

Proceedings - IEEE 34th International Conference on Data Engineering, ICDE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 101-112 8509240.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Luo, Y, Qin, X, Tang, N & Li, G 2018, Deepeye: towards automatic data visualization. in Proceedings - IEEE 34th International Conference on Data Engineering, ICDE 2018., 8509240, Institute of Electrical and Electronics Engineers Inc., pp. 101-112, 34th IEEE International Conference on Data Engineering, ICDE 2018, Paris, France, 16/4/18. https://doi.org/10.1109/ICDE.2018.00019
Luo Y, Qin X, Tang N, Li G. Deepeye: towards automatic data visualization. In Proceedings - IEEE 34th International Conference on Data Engineering, ICDE 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 101-112. 8509240 https://doi.org/10.1109/ICDE.2018.00019
Luo, Yuyu ; Qin, Xuedi ; Tang, Nan ; Li, Guoliang. / Deepeye : towards automatic data visualization. Proceedings - IEEE 34th International Conference on Data Engineering, ICDE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 101-112
@inproceedings{a71c1d27ca6148bf9d155affc9c22b78,
title = "Deepeye: towards automatic data visualization",
abstract = "Data visualization is invaluable for explaining the significance of data to people who are visually oriented. The central task of automatic data visualization is, given a dataset, to visualize its compelling stories by transforming the data (e.g., selecting attributes, grouping and binning values) and deciding the right type of visualization (e.g., bar or line charts). We present DEEPEYE, a novel system for automatic data visualization that tackles three problems: (1) Visualization recognition: given a visualization, is it 'good or 'bad'? (2) Visualization ranking: given two visualizations, which one is 'better'? And (3) Visualization selection: given a dataset, how to find top-k visualizations? DEEPEYE addresses (1) by training a binary classifier to decide whether a particular visualization is good or bad. It solves (2) from two perspectives: (i) Machine learning: it uses a supervised learning-To-rank model to rank visualizations; and (ii) Expert rules: it relies on experts' knowledge to specify partial orders as rules. Moreover, a 'boring' dataset may become interesting after data transformations (e.g., binning and grouping), which forms a large search space. We also discuss optimizations to efficiently compute top-k visualizations, for approaching (3). Extensive experiments verify the effectiveness of DEEPEYE.",
keywords = "Automatic, data visualization",
author = "Yuyu Luo and Xuedi Qin and Nan Tang and Guoliang Li",
year = "2018",
month = "10",
day = "24",
doi = "10.1109/ICDE.2018.00019",
language = "English",
pages = "101--112",
booktitle = "Proceedings - IEEE 34th International Conference on Data Engineering, ICDE 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Deepeye

T2 - towards automatic data visualization

AU - Luo, Yuyu

AU - Qin, Xuedi

AU - Tang, Nan

AU - Li, Guoliang

PY - 2018/10/24

Y1 - 2018/10/24

N2 - Data visualization is invaluable for explaining the significance of data to people who are visually oriented. The central task of automatic data visualization is, given a dataset, to visualize its compelling stories by transforming the data (e.g., selecting attributes, grouping and binning values) and deciding the right type of visualization (e.g., bar or line charts). We present DEEPEYE, a novel system for automatic data visualization that tackles three problems: (1) Visualization recognition: given a visualization, is it 'good or 'bad'? (2) Visualization ranking: given two visualizations, which one is 'better'? And (3) Visualization selection: given a dataset, how to find top-k visualizations? DEEPEYE addresses (1) by training a binary classifier to decide whether a particular visualization is good or bad. It solves (2) from two perspectives: (i) Machine learning: it uses a supervised learning-To-rank model to rank visualizations; and (ii) Expert rules: it relies on experts' knowledge to specify partial orders as rules. Moreover, a 'boring' dataset may become interesting after data transformations (e.g., binning and grouping), which forms a large search space. We also discuss optimizations to efficiently compute top-k visualizations, for approaching (3). Extensive experiments verify the effectiveness of DEEPEYE.

AB - Data visualization is invaluable for explaining the significance of data to people who are visually oriented. The central task of automatic data visualization is, given a dataset, to visualize its compelling stories by transforming the data (e.g., selecting attributes, grouping and binning values) and deciding the right type of visualization (e.g., bar or line charts). We present DEEPEYE, a novel system for automatic data visualization that tackles three problems: (1) Visualization recognition: given a visualization, is it 'good or 'bad'? (2) Visualization ranking: given two visualizations, which one is 'better'? And (3) Visualization selection: given a dataset, how to find top-k visualizations? DEEPEYE addresses (1) by training a binary classifier to decide whether a particular visualization is good or bad. It solves (2) from two perspectives: (i) Machine learning: it uses a supervised learning-To-rank model to rank visualizations; and (ii) Expert rules: it relies on experts' knowledge to specify partial orders as rules. Moreover, a 'boring' dataset may become interesting after data transformations (e.g., binning and grouping), which forms a large search space. We also discuss optimizations to efficiently compute top-k visualizations, for approaching (3). Extensive experiments verify the effectiveness of DEEPEYE.

KW - Automatic

KW - data visualization

UR - http://www.scopus.com/inward/record.url?scp=85048789999&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048789999&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2018.00019

DO - 10.1109/ICDE.2018.00019

M3 - Conference contribution

SP - 101

EP - 112

BT - Proceedings - IEEE 34th International Conference on Data Engineering, ICDE 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -