Automatic Synthesis of Visualization Design Knowledge Bases

2026-01-27

AI Summary

This work proposes a data-driven approach to automatically construct a knowledge base of visualization design principles, overcoming the limitations of traditional rule-based methods that rely on manual curation and lack scalability. By applying feature extraction and forward–backward feature selection algorithms to a large-scale corpus of visualizations, the method learns interpretable design rules without human intervention. These rules are then organized into a structured knowledge base using knowledge graph techniques. The resulting system demonstrates strong scalability and cross-domain adaptability. Experimental results show consistent improvements of 1–15% in accuracy over existing methods on standard benchmarks for predicting effective visual designs, and achieve 97% accuracy on genomics visualization tasks, validating the approach’s generality and effectiveness.

Technology Category

• Data Mining & Knowledge Management: Data Visualization & Summarization
• Computer Vision: Visual Reasoning & Symbolic Representations
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Web data visualization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• visualization design
• knowledge base
• manual rules
• domain extensibility
• design representation

Innovation

• data-driven synthesis
• visualization knowledge base
• automated feature extraction
• interpretable design
• cross-domain adaptation