Automatic Synthesis of Visualization Design Knowledge Bases

TL;DR

This paper introduces data-driven methods to automatically synthesize visualization design knowledge bases, enabling more flexible and accurate design recommendations across different domains.

Contribution

It presents a novel automated approach for creating visualization knowledge bases, moving beyond manual rules and demonstrating effectiveness in diverse domains.

Findings

Synthesized knowledge bases improve design prediction accuracy by 1-15%.

The approach achieves up to 97% accuracy in genomics visualization.

Provides general, interpretable design features.

Abstract

Formal representations of the visualization design space, such as knowledge bases and graphs, consolidate design practices into a shared resource and enable automated reasoning and interpretable design recommendations. However, prior approaches typically depend on fixed, manually authored rules, making it difficult to build novel representations or extend them for different visualization domains. Instead, we propose data-driven methods that automatically synthesize visualization design knowledge bases. Specifically, our methods (1) extract candidate design features from a visualization corpus, (2) select features forward and backward, and (3) render the final knowledge base. In our benchmark evaluation compared to Draco 2, our synthesized knowledge base offers general and interpretable design features and improves the accuracy of predicting effective designs by 1-15% in varied training and test sets. When we apply our approach to genomics visualization, the synthesized knowledge base includes sensible features with accuracy up to 97%, demonstrating the applicability of our approach to other visualization domains.