ICE: An Interactive Configuration Explorer for High Dimensional Categorical Parameter Spaces

Tyagi, Anjul; Cao, Zhen; Estro, Tyler; Zadok, Erez; Mueller, Klaus

doi:10.1109/vast47406.2019.8986923

Cited by 7 publications

(3 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the work related to infographic generation, there is considerable research in developing recommendation systems for data visualizations (charts). These techniques can be broadly classified into two categories: rule‐based [SI11, Mac86, RKMG94, TCE * 19, CKM * 19] and data‐driven techniques [HBL * 19, DD19, DD19, SMWH16, KTB * 19, TXM20]. The rule‐based techniques [SI11, Mac86] introduced methods to generate a latent space of charts using compositional algebra, which was later improved by SAGE [RKMG94].…”

Section: Related Workmentioning

confidence: 99%

Infographics Wizard: Flexible Infographics Authoring and Design Exploration

Tyagi

Zhao

Patel

et al. 2022

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

Infographics are an aesthetic visual representation of information following specific design principles of human perception. Designing infographics can be a tedious process for non‐experts and time‐consuming, even for professional designers. With the help of designers, we propose a semi‐automated infographic framework for general structured and flow‐based infographic design generation. For novice designers, our framework automatically creates and ranks infographic designs for a user‐provided text with no requirement for design input. However, expert designers can still provide custom design inputs to customize the infographics. We will also contribute an individual visual group (VG) designs dataset (in SVG), along with a 1k complete infographic image dataset with segmented VGs in this work. Evaluation results confirm that by using our framework, designers from all expertise levels can generate generic infographic designs faster than existing methods while maintaining the same quality as hand‐designed infographics templates.

show abstract

Section: Related Workmentioning

confidence: 99%

Infographics Wizard: Flexible Infographics Authoring and Design Exploration

Tyagi

Zhao

Patel

et al. 2022

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

show abstract

“…Automated Neural Network Architecture search has a long history [41,55]. Moreover, after the recent research showing promising results with the application of deep neural networks in the areas of Computer Vision [18,29,32,33], Natural Language Processing [40,57,60], Storage Systems [10,63] and other applications [30,64], the problem of finding the best working neural network architecture has escalated. Neural Networks are constantly growing in size, for example, AlexNet [29] developed in the year 2012 for image classification task had 8 layers, which was followed by VGGNet [59] in the year 2014 which had 19 layers.…”

Section: Related Work 21 Automatic Neural Network Architecture Searchmentioning

confidence: 99%

NAS-Navigator: Visual Steering for Explainable One-Shot Deep Neural Network Synthesis

Tyagi¹,

Xie²,

Mueller³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Fig. 1. Our visual steering interface purposed to guide analysts in the task of constructing the best performing deep neural network architecture for a given application using a one-shot search algorithm. The first section is the Lego View where the analyst can create and edit different components of a large neural network with simple drag and drop operations. The Lego View visualizes the different neural network components along with their parameters. An initial large neural network is treated as a super graph (shown in the Graph View) and the problem of finding the best performing neural network architecture is framed as searching for the respective subgraph in this super graph. The Graph View visualizes the super graph where each node is a block (sequence of neural network components). The One-Shot Search algorithm evaluates the subgraphs of this super graph iteratively, gauges their accuracy with regards to a test dataset and provides a fitness score for each node in the graph (Block Information view). The subgraphs are then projected as points into the scatterplot in the Search Space view and colored based on their evaluation accuracy. Analysts can filter and analyze a specific region in the subgraph search space with zoom and pan operations in the Search Space View. Finally, all blocks with high fitness scores are combined to create the best performing candidate neural network architecture.

show abstract

“…Parallel Coordinate Plots (PCPs) [20] have been a popular choice for HD data visualization since they can convey a large number of dimensions without distortions. PCPs are considered a storytelling method where each ordering of axes presents a particular story from the HD data, and techniques like axes repetition, data scaling, and axes inversion have been suggested to enable a persuasive narration of a story [18,40,46,47]. Previous storytelling work with PCPs mainly focused on axes arrangement based on common data properties like correlation, clustering, and the number of line crossings [43]; they detect these properties in every pair of dimensions in the data and then find the corresponding axes arrangement using the traveling salesman problem (TSP) [15,53] over the computed scores.…”

mentioning

confidence: 99%