# GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding

arXiv: https://arxiv.org/abs/2405.03104 · HTML: https://mlsanity.com/paper/2405.03104/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 6 May 2024.

## Builds on (most cited first, 29 of 29)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [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)
- [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)
- [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)
- [SelfDoc: Self-Supervised Document Representation Learning](https://mlsanity.com/paper/2106.03331/) (2021)
- [LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding](https://mlsanity.com/paper/2202.13669/) (2022)
- [BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents](https://mlsanity.com/paper/2108.04539/) (2021)
- [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://mlsanity.com/paper/2104.08836/) (2021)
- [Unified Pretraining Framework for Document Understanding](https://mlsanity.com/paper/2204.10939/) (2022)
- [End-to-end Document Recognition and Understanding with Dessurt](https://mlsanity.com/paper/2203.16618/) (2022)
- [GeoLayoutLM: Geometric Pre-training for Visual Information Extraction](https://mlsanity.com/paper/2304.10759/) (2023)
- [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)
- [Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks](https://mlsanity.com/paper/2208.11168/) (2022)
- [Privacy-Aware Document Visual Question Answering](https://mlsanity.com/paper/2312.10108/) (2023)
- [Visual FUDGE: Form Understanding via Dynamic Graph Editing](https://mlsanity.com/paper/2105.08194/) (2021)
- [SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation](https://mlsanity.com/paper/2305.04609/) (2023)
- [SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation](https://mlsanity.com/paper/2305.00795/) (2023)
- [DocGraphLM: Documental Graph Language Model for Information Extraction](https://mlsanity.com/paper/2401.02823/) (2024)
- [Language Independent Neuro-Symbolic Semantic Parsing for Form Understanding](https://mlsanity.com/paper/2305.04460/) (2023)

## Built on by (most cited first, 3 of 3)

- [Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review](https://mlsanity.com/paper/2408.06345/) (2024)
- [NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA](https://mlsanity.com/paper/2411.03730/) (2024)
- [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)

## Abstract (arXiv)

This paper presents GeoContrastNet, a language-agnostic framework to structured document understanding (DU) by integrating a contrastive learning objective with graph attention networks (GATs), emphasizing the significant role of geometric features. We propose a novel methodology that combines geometric edge features with visual features within an overall two-staged GAT-based framework, demonstrating promising results in both link prediction and semantic entity recognition performance. Our findings reveal that combining both geometric and visual features could match the capabilities of large DU models that rely heavily on Optical Character Recognition (OCR) features in terms of performance accuracy and efficiency. This approach underscores the critical importance of relational layout information between the named text entities in a semi-structured layout of a page. Specifically, our results highlight the model's proficiency in identifying key-value relationships within the FUNSD dataset for forms and also discovering the spatial relationships in table-structured layouts for RVLCDIP business invoices. Our code and pretrained models will be accessible on our official GitHub.