# A Graphical Approach to Document Layout Analysis

arXiv: https://arxiv.org/abs/2308.02051 · HTML: https://mlsanity.com/paper/2308.02051/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 3 Aug 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [DiT: Self-supervised Pre-training for Document Image Transformer](https://mlsanity.com/paper/2203.02378/) (2022)
- [Topology Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1710.10370/) (2017)
- [StructuralLM: Structural Pre-training for Form Understanding](https://mlsanity.com/paper/2105.11210/) (2021)
- [Graph Convolution for Multimodal Information Extraction from Visually Rich Documents](https://mlsanity.com/paper/1903.11279/) (2019)
- [Unified Pretraining Framework for Document Understanding](https://mlsanity.com/paper/2204.10939/) (2022)
- [Document AI: Benchmarks, Models and Applications](https://mlsanity.com/paper/2111.08609/) (2021)
- [VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations](https://mlsanity.com/paper/2105.06220/) (2021)
- [Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models](https://mlsanity.com/paper/2005.11017/) (2020)
- [A Saliency-based Convolutional Neural Network for Table and Chart Detection in Digitized Documents](https://mlsanity.com/paper/1804.06236/) (2018)
- [Table understanding in structured documents](https://mlsanity.com/paper/1904.12577/) (2019)
- [Graph Neural Networks and Representation Embedding for Table Extraction in PDF Documents](https://mlsanity.com/paper/2208.11203/) (2022)
- [Pipelines for Procedural Information Extraction from Scientific Literature: Towards Recipes using Machine Learning and Data Science](https://mlsanity.com/paper/1912.07747/) (2019)

## Built on by (most cited first, 8 of 8)

- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction](https://mlsanity.com/paper/2410.21169/) (2024)
- [DLAFormer: An End-to-End Transformer For Document Layout Analysis](https://mlsanity.com/paper/2405.11757/) (2024)
- [UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis](https://mlsanity.com/paper/2503.15893/) (2025)
- [UnSupDLA: Towards Unsupervised Document Layout Analysis](https://mlsanity.com/paper/2406.06236/) (2024)
- [PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction](https://mlsanity.com/paper/2512.10888/) (2025)
- [R2-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation](https://mlsanity.com/paper/2508.01475/) (2025)
- [Visual-Aware Representation of Web Pages for Machine Learning Applications](https://mlsanity.com/paper/2608.18727/) (2026)

## Abstract (arXiv)

Document layout analysis (DLA) is the task of detecting the distinct, semantic content within a document and correctly classifying these items into an appropriate category (e.g., text, title, figure). DLA pipelines enable users to convert documents into structured machine-readable formats that can then be used for many useful downstream tasks. Most existing state-of-the-art (SOTA) DLA models represent documents as images, discarding the rich metadata available in electronically generated PDFs. Directly leveraging this metadata, we represent each PDF page as a structured graph and frame the DLA problem as a graph segmentation and classification problem. We introduce the Graph-based Layout Analysis Model (GLAM), a lightweight graph neural network competitive with SOTA models on two challenging DLA datasets - while being an order of magnitude smaller than existing models. In particular, the 4-million parameter GLAM model outperforms the leading 140M+ parameter computer vision-based model on 5 of the 11 classes on the DocLayNet dataset. A simple ensemble of these two models achieves a new state-of-the-art on DocLayNet, increasing mAP from 76.8 to 80.8. Overall, GLAM is over 5 times more efficient than SOTA models, making GLAM a favorable engineering choice for DLA tasks.