mlsanityData to 14 Oct 2026

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

arXiv 2208.11168 ↗First posted 23 Aug 2022cs.CVcited by 17

Not on the map. Why?

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.

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

22 of 36 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2019Towards VQA Models That Can Readcited by 1,718
  5. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  6. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 553
  7. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 408
  8. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 349
  9. 2021ICDAR2019 Competition on Scanned Receipt OCR and Information Extractioncited by 256
  10. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 256
  11. 2015Evaluation of Deep Convolutional Nets for Document Image Classification and Retrievalcited by 213
  12. 2021Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformercited by 134
10 more
  1. 2021PubTables-1M: Towards comprehensive table extraction from unstructured documentscited by 126
  2. 2020PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networkscited by 72
  3. 2020Table Structure Recognition using Top-Down and Bottom-Up Cuescited by 53
  4. 2021Neural Collaborative Graph Machines for Table Structure Recognitioncited by 30
  5. 2021TGRNet: A Table Graph Reconstruction Network for Table Structure Recognitioncited by 27
  6. 2019Deep Visual Template-Free Form Parsingcited by 24
  7. 2022DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformercited by 19
  8. 2021Visual FUDGE: Form Understanding via Dynamic Graph Editingcited by 15
  9. 2020Revising FUNSD dataset for key-value detection in document imagescited by 10
  10. 2021Graph-based Deep Generative Modelling for Document Layout Generationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 6; 2025: 3; 2026: 2.

17 papers.

Sort:

By area:

  1. 2023Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Predictioncited by 23
  2. 2024RoDLA: Benchmarking the Robustness of Document Layout Analysis Modelscited by 13
  3. 2023SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentationcited by 7
  4. 2025Benchmarking Graph Neural Networks for Document Layout Analysis in Public Affairscited by 7
  5. 2024DocGraphLM: Documental Graph Language Model for Information Extractioncited by 6
  6. 2023CTE: A Dataset for Contextualized Table Extractioncited by 3
  7. 2024GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understandingcited by 3
  8. 2023PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysiscited by 2
  9. 2024Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidencecited by 2
  10. 2024UnSupDLA: Towards Unsupervised Document Layout Analysiscited by 2
  11. 2024Leveraging Inter-Chunk Interactions for Enhanced Retrieval in Large Language Model-Based Question Answeringcited by 2
  12. 2025Relation-Rich Visual Document Generator for Visual Information Extractioncited by 2
5 more
  1. 2023Language Independent Neuro-Symbolic Semantic Parsing for Form Understandingcited by 1
  2. 2025MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Usecited by 1
  3. 2026Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligencecited by 1
  4. 2023Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout Analysiscited by 0
  5. 2026Visual-Aware Representation of Web Pages for Machine Learning Applicationscited by 0