DeepEye: Towards Automatic Data Visualization

Towards Automated Infographic Design: Deep Learning-based Auto-Extraction of Extensible Timeline

“…Foregoing explicit rules, researchers have recently designed learningbased systems that directly learn visualization designs from visualization corpora. DeepEye [33] applies ML models and design rules to determine whether a visualization is "good" or "bad" and recommends the "good" candidates. Data2Vis [14] uses a Recurrent Neural Network to automatically translate JSON-encoded datasets to Vega-lite [45] specifications.…”

VizNet

“…Draco-Learn [49] learns tradeoffs between constraints in Draco. DeepEye [41] combines rule-based visualization generation with models trained to classify a visualization as "good" or "bad" and rank lists of visualizations. VizML [27] uses neural networks to predict visualization design choices from a corpus of one million dataset-visualization pairs harvested from a popular online visualization tool.…”

View recommendation for visual data exploration

“…Quantifying Interestingness: There is a lack of unified and consistent formulation of interestingness measure. A number of methods have been proposed to quantify intrestingness such as, deviation-based, similarity-based and perception-based [6,10,47].…”

“…Motivated by the need for an efficient and effective visual data exploration process, several solutions have been proposed towards automatically finding and recommending interesting data visualizations [6][7][8][9][10][11][12]. The main idea underlying those solutions is to automatically generate all possible visualizations, and recommend the top-k interesting visualizations, where an interestingness of a view is quantified according to some utility function.…”

“…Moreover, the hardest part of visualization recommendation is to quantify what would be interesting for the analyst. Consequently, the visualization recommendation problem has been approached from different angles, such as deviation-based/similarity-based methods that 1 Figure 1.1: Data exploration process-Key steps quantify interestingness as a similarity/distance metric [6,[13][14][15], user-actions-based methods that quantify interestingness in term of user's intent, which is inferred by her present actions or by historic data [7,16], perception-based methods, that learn human perception and use it to mine and recommend interesting visualizations [10][11][12].…”