From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models

• URL: http://arxiv.org/abs/2403.12027v2
• Date: Mon, 25 Mar 2024 17:39:10 GMT
• Title: From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models
• Authors: Kung-Hsiang Huang, Hou Pong Chan, Yi R. Fung, Haoyi Qiu, Mingyang Zhou, Shafiq Joty, Shih-Fu Chang, Heng Ji,
• Abstract summary: Data visualization in the form of charts plays a pivotal role in data analysis, offering critical insights and aiding in informed decision-making. Large foundation models, such as large language models, have revolutionized various natural language processing tasks. This survey paper serves as a comprehensive resource for researchers and practitioners in the fields of natural language processing, computer vision, and data analysis.
• Score: 98.41645229835493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data visualization in the form of charts plays a pivotal role in data analysis, offering critical insights and aiding in informed decision-making. Automatic chart understanding has witnessed significant advancements with the rise of large foundation models in recent years. Foundation models, such as large language models, have revolutionized various natural language processing tasks and are increasingly being applied to chart understanding tasks. This survey paper provides a comprehensive overview of the recent developments, challenges, and future directions in chart understanding within the context of these foundation models. We review fundamental building blocks crucial for studying chart understanding tasks. Additionally, we explore various tasks and their evaluation metrics and sources of both charts and textual inputs. Various modeling strategies are then examined, encompassing both classification-based and generation-based approaches, along with tool augmentation techniques that enhance chart understanding performance. Furthermore, we discuss the state-of-the-art performance of each task and discuss how we can improve the performance. Challenges and future directions are addressed, highlighting the importance of several topics, such as domain-specific charts, lack of efforts in developing evaluation metrics, and agent-oriented settings. This survey paper serves as a comprehensive resource for researchers and practitioners in the fields of natural language processing, computer vision, and data analysis, providing valuable insights and directions for future research in chart understanding leveraging large foundation models. The studies mentioned in this paper, along with emerging new research, will be continually updated at: https://github.com/khuangaf/Awesome-Chart-Understanding.

Related papers

• ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization [32.19963543411396]
  This study constructs a large-scale dataset of comprehensive chart-caption pairs and fine-tuning instructions on each chart. We propose an innovative chart summarization method, ChartThinker, which synthesizes deep analysis based on chains of thought. Built upon the curated datasets, our trained model consistently exhibits superior performance in chart summarization tasks.
  arXiv  Detail & Related papers  (2024-03-17T14:49:09Z)
• Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learning [53.81365215811222]
  We provide a review and summary of the latest approaches, strategies, and insights that address distribution shifts within the context of graph learning. We categorize existing graph learning methods into several essential scenarios, including graph domain adaptation learning, graph out-of-distribution learning, and graph continual learning. We discuss the potential applications and future directions for graph learning under distribution shifts with a systematic analysis of the current state in this field.
  arXiv  Detail & Related papers  (2024-02-26T07:52:40Z)
• Few-Shot Learning on Graphs: from Meta-learning to Pre-training and Prompting [56.25730255038747]
  This survey endeavors to synthesize recent developments, provide comparative insights, and identify future directions. We systematically categorize existing studies into three major families: meta-learning approaches, pre-training approaches, and hybrid approaches. We analyze the relationships among these methods and compare their strengths and limitations.
  arXiv  Detail & Related papers  (2024-02-02T14:32:42Z)
• A Survey of Data-Efficient Graph Learning [16.053913182723143]
  We introduce a novel concept of Data-Efficient Graph Learning (DEGL) as a research frontier. We systematically review recent advances on several key aspects, including self-supervised graph learning, semi-supervised graph learning, and few-shot graph learning.
  arXiv  Detail & Related papers  (2024-02-01T09:28:48Z)
• Towards Graph Foundation Models: A Survey and Beyond [66.37994863159861]
  Foundation models have emerged as critical components in a variety of artificial intelligence applications. The capabilities of foundation models to generalize and adapt motivate graph machine learning researchers to discuss the potential of developing a new graph learning paradigm. This article introduces the concept of Graph Foundation Models (GFMs), and offers an exhaustive explanation of their key characteristics and underlying technologies.
  arXiv  Detail & Related papers  (2023-10-18T09:31:21Z)
• A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions [64.84521350148513]
  Graphs represent interconnected structures prevalent in a myriad of real-world scenarios. Effective graph analytics, such as graph learning methods, enables users to gain profound insights from graph data. However, these methods often suffer from data imbalance, a common issue in graph data where certain segments possess abundant data while others are scarce. This necessitates the emerging field of imbalanced learning on graphs, which aims to correct these data distribution skews for more accurate and representative learning outcomes.
  arXiv  Detail & Related papers  (2023-08-26T09:11:44Z)
• GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking [17.7473474499538]
  Large language models like ChatGPT have become indispensable to artificial general intelligence. In this study, we conduct an investigation to assess the proficiency of LLMs in comprehending graph data. Our findings contribute valuable insights towards bridging the gap between language models and graph understanding.
  arXiv  Detail & Related papers  (2023-05-24T11:53:19Z)
• Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities [128.55790219377315]
  Graph neural networks have emerged as a leading architecture for many graph-level tasks. graph pooling is indispensable for obtaining a holistic graph-level representation of the whole graph.
  arXiv  Detail & Related papers  (2022-04-15T04:02:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.