# Chart2Vec: A Universal Embedding of Context-Aware Visualizations

arXiv: https://arxiv.org/abs/2306.08304 · HTML: https://mlsanity.com/paper/2306.08304/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2023.

## Built on by (most cited first, 4 of 4)

- [Conversational AI Threads for Visualizing Multidimensional Datasets](https://mlsanity.com/paper/2311.05590/) (2023)
- [Safire: Similarity Framework for Visualization Retrieval](https://mlsanity.com/paper/2510.16662/) (2025)
- [Do Large Language Models Understand Data Visualization Principles?](https://mlsanity.com/paper/2602.20084/) (2026)
- [Show Me the Infographic I Imagine: Intent-Aware Infographic Retrieval for Authoring Support](https://mlsanity.com/paper/2604.07989/) (2026)

## Abstract (arXiv)

The advances in AI-enabled techniques have accelerated the creation and automation of visualizations in the past decade. However, presenting visualizations in a descriptive and generative format remains a challenge. Moreover, current visualization embedding methods focus on standalone visualizations, neglecting the importance of contextual information for multi-view visualizations. To address this issue, we propose a new representation model, Chart2Vec, to learn a universal embedding of visualizations with context-aware information. Chart2Vec aims to support a wide range of downstream visualization tasks such as recommendation and storytelling. Our model considers both structural and semantic information of visualizations in declarative specifications. To enhance the context-aware capability, Chart2Vec employs multi-task learning on both supervised and unsupervised tasks concerning the cooccurrence of visualizations. We evaluate our method through an ablation study, a user study, and a quantitative comparison. The results verified the consistency of our embedding method with human cognition and showed its advantages over existing methods.