 Honorable Mention

KG4Vis: A Knowledge Graph-Based Approach for Visualization Recommendation



Haotian Li, Yong Wang, Songheng Zhang, Yangqiu Song, Huamin Qu

 External link (DOI) 

 View presentation:2021-10-27T18:00:00ZGMT-0600Change your timezone on the schedule page
2021-10-27T18:00:00Z

Exemplar figure, described by caption below — This figure illustrates the overall workflow of KG4Vis. We extract features from existing dataset-visualization pairs and construct a knowledge graph (KG). Then the embeddings of entities and relations in the KG are learned. Based on the embeddings, we conduct inference on a new dataset and finally recommend multiple visualizations. Also, various rules are extracted based on the embeddings and presented together with recommended visualizations to improve the interpretability of visualization recommendation.

Fast forward

Direct link to video on YouTube: https://youtu.be/RVX1jFGNLdw

Abstract

Visualization recommendation or automatic visualization generation can significantly lower the barriers for general users to rapidly create effective data visualizations, especially for those users without a background in data visualizations. However, existing rule-based approaches require tedious manual specifications of visualization rules by visualization experts. Other machine learning-based approaches often work like black-box and are difficult to understand why a specific visualization is recommended, limiting the wider adoption of these approaches. This paper fills the gap by presenting KG4Vis, a knowledge graph (KG)-based approach for visualization recommendation. It does not require manual specifications of visualization rules and can also guarantee good explainability. Specifically, we propose a framework for building knowledge graphs, consisting of three types of entities (i.e., data features, data columns and visualization design choices) and the relations between them, to model the mapping rules between data and effective visualizations. A TransE-based embedding technique is employed to learn the embeddings of both entities and relations of the knowledge graph from existing dataset-visualization pairs. Such embeddings intrinsically model the desirable visualization rules. Then, given a new dataset, effective visualizations can be inferred from the knowledge graph with semantically meaningful rules. We conducted extensive evaluations to assess the proposed approach, including quantitative comparisons, case studies and expert interviews. The results demonstrate the effectiveness of our approach.