MuVE: Efficient Multi-Objective View Recommendation for Visual Data ExplorationDocUID: 2016-003 Full Text: PDF
Author: Humaira Ehsan, Mohamed A. Sharaf, Panos K. Chrysanthis
Abstract: To support effective data exploration, there is a well-recognized need for solutions that can automatically recommend interesting visualizations, which reveal useful insights into the analyzed data. However, such visualizations come at the expense of high data processing costs, where a large number of views are generated to evaluate their usefulness. Those costs are further escalated in the presence of numerical dimensional attributes, due to the potentially large number of possible binning aggregations, which lead to a drastic increase in the number of possible visualizations. To address that challenge, in this paper we propose the MuVE scheme for Multi-Objective View Recommendation for Visual Data Exploration. MuVE introduces a hybrid multi-objective utility function, which captures the impact of binning on the utility of visualizations. Consequently, novel algorithms are proposed for the efficient recommendation of data visualizations that are based on numerical dimensions. The main idea underlying MuVE is to incrementally and progressively assess the different benefits provided by a visualization, which allows an early pruning of a large number of unnecessary operations. Our extensive experimental results show the significant gains provided by our proposed scheme.
Published In: 32nd IEEE International Conference on Data Engineering
Year Published: 2016
Project: Data Exploration Subject Area: Data Visualization
Publication Type: Conference Paper
Sponsor: NSF OIA-1028162