# PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph

arXiv: https://arxiv.org/abs/2407.00742 · HTML: https://mlsanity.com/paper/2407.00742/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 39 references that are in the map.
- First posted on arXiv 30 Jun 2024.

## Builds on (most cited first, 10 of 10)

- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images](https://mlsanity.com/paper/2111.15491/) (2021)
- [Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions](https://mlsanity.com/paper/2105.09392/) (2021)
- [Towards General-Purpose Representation Learning of Polygonal Geometries](https://mlsanity.com/paper/2209.15458/) (2022)
- [Deep Learning for Classification Tasks on Geospatial Vector Polygons](https://mlsanity.com/paper/1806.03857/) (2018)
- [Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes](https://mlsanity.com/paper/2306.12203/) (2023)
- [DDSL: Deep Differentiable Simplex Layer for Learning Geometric Signals](https://mlsanity.com/paper/1901.11082/) (2019)
- [Translating Place-Related Questions to GeoSPARQL Queries](https://mlsanity.com/paper/2205.03067/) (2022)
- [Agglomeration of Polygonal Grids using Graph Neural Networks with applications to Multigrid solvers](https://mlsanity.com/paper/2210.17457/) (2022)

## Built on by (most cited first, 10 of 10)

- [Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications](https://mlsanity.com/paper/2408.14806/) (2024)
- [Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions](https://mlsanity.com/paper/2502.18470/) (2025)
- [Geo2Vec: Shape- and Distance-Aware Neural Representation of Geospatial Entities](https://mlsanity.com/paper/2508.19305/) (2025)
- [Learning Sewing Patterns via Latent Flow Matching of Implicit Fields](https://mlsanity.com/paper/2601.17740/) (2026)
- [Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)](https://mlsanity.com/paper/2604.07522/) (2026)
- [Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models](https://mlsanity.com/paper/2606.02374/) (2026)
- [VisDiff: SDF-Guided Polygon Generation for Visibility Reconstruction and Recognition](https://mlsanity.com/paper/2410.05530/) (2024)
- [TrajGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations](https://mlsanity.com/paper/2605.06990/) (2026)
- [Geometry-Aware Reinforcement Learning for 2D Irregular Nesting](https://mlsanity.com/paper/2606.10611/) (2026)
- [Automated Quality Assessment of Geospatial Vector Data: A GeoAI Approach using Spatial Representation Learning](https://mlsanity.com/paper/2606.28390/) (2026)

## Abstract (arXiv)

Polygon representation learning is essential for diverse applications, encompassing tasks such as shape coding, building pattern classification, and geographic question answering. While recent years have seen considerable advancements in this field, much of the focus has been on single polygons, overlooking the intricate inner- and inter-polygonal relationships inherent in multipolygons. To address this gap, our study introduces a comprehensive framework specifically designed for learning representations of polygonal geometries, particularly multipolygons. Central to our approach is the incorporation of a heterogeneous visibility graph, which seamlessly integrates both inner- and inter-polygonal relationships. To enhance computational efficiency and minimize graph redundancy, we implement a heterogeneous spanning tree sampling method. Additionally, we devise a rotation-translation invariant geometric representation, ensuring broader applicability across diverse scenarios. Finally, we introduce Multipolygon-GNN, a novel model tailored to leverage the spatial and semantic heterogeneity inherent in the visibility graph. Experiments on five real-world and synthetic datasets demonstrate its ability to capture informative representations for polygonal geometries. Code and data are available at hrefhttps://github.com/dyu62/PolyGNNgithub.com/dyu62/PolyGNN.