# Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks

arXiv: https://arxiv.org/abs/2208.11168 · HTML: https://mlsanity.com/paper/2208.11168/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 23 Aug 2022.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [DocFormer: End-to-End Transformer for Document Understanding](https://mlsanity.com/paper/2106.11539/) (2021)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer](https://mlsanity.com/paper/2102.09550/) (2021)
- [PubTables-1M: Towards comprehensive table extraction from unstructured documents](https://mlsanity.com/paper/2110.00061/) (2021)
- [PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks](https://mlsanity.com/paper/2004.07464/) (2020)
- [Table Structure Recognition using Top-Down and Bottom-Up Cues](https://mlsanity.com/paper/2010.04565/) (2020)
- [Neural Collaborative Graph Machines for Table Structure Recognition](https://mlsanity.com/paper/2111.13359/) (2021)
- [TGRNet: A Table Graph Reconstruction Network for Table Structure Recognition](https://mlsanity.com/paper/2106.10598/) (2021)
- [Deep Visual Template-Free Form Parsing](https://mlsanity.com/paper/1909.02576/) (2019)
- [DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer](https://mlsanity.com/paper/2201.11438/) (2022)
- [Visual FUDGE: Form Understanding via Dynamic Graph Editing](https://mlsanity.com/paper/2105.08194/) (2021)
- [Revising FUNSD dataset for key-value detection in document images](https://mlsanity.com/paper/2010.05322/) (2020)
- [Graph-based Deep Generative Modelling for Document Layout Generation](https://mlsanity.com/paper/2107.04357/) (2021)

## Built on by (most cited first, 17 of 17)

- [Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction](https://mlsanity.com/paper/2310.11016/) (2023)
- [RoDLA: Benchmarking the Robustness of Document Layout Analysis Models](https://mlsanity.com/paper/2403.14442/) (2024)
- [SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation](https://mlsanity.com/paper/2305.00795/) (2023)
- [Benchmarking Graph Neural Networks for Document Layout Analysis in Public Affairs](https://mlsanity.com/paper/2505.14699/) (2025)
- [DocGraphLM: Documental Graph Language Model for Information Extraction](https://mlsanity.com/paper/2401.02823/) (2024)
- [CTE: A Dataset for Contextualized Table Extraction](https://mlsanity.com/paper/2302.01451/) (2023)
- [GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding](https://mlsanity.com/paper/2405.03104/) (2024)
- [PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis](https://mlsanity.com/paper/2304.11810/) (2023)
- [Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidence](https://mlsanity.com/paper/2403.18183/) (2024)
- [UnSupDLA: Towards Unsupervised Document Layout Analysis](https://mlsanity.com/paper/2406.06236/) (2024)
- [Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answering](https://mlsanity.com/paper/2408.02907/) (2024)
- [Relation-Rich Visual Document Generator for Visual Information Extraction](https://mlsanity.com/paper/2504.10659/) (2025)
- [Language Independent Neuro-Symbolic Semantic Parsing for Form Understanding](https://mlsanity.com/paper/2305.04460/) (2023)
- [MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use](https://mlsanity.com/paper/2511.17881/) (2025)
- [Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence](https://mlsanity.com/paper/2609.32041/) (2026)
- [Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout Analysis](https://mlsanity.com/paper/2308.15517/) (2023)
- [Visual-Aware Representation of Web Pages for Machine Learning Applications](https://mlsanity.com/paper/2608.18727/) (2026)

## Abstract (arXiv)

Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Networks (GNNs) has become crucial in various document-related tasks since they can unravel important structural patterns, fundamental in key information extraction processes. Previous works in the literature propose task-driven models and do not take into account the full power of graphs. We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model, to solve different tasks given different types of documents. We evaluated our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection. Our code is freely accessible on https://github.com/andreagemelli/doc2graph.