[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.1145/3637528.3671738acmconferencesArticle/Chapter ViewAbstractPublication PageskddConference Proceedingsconference-collections
research-article
Open access

PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph

Published: 24 August 2024 Publication History

Abstract

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.

Supplemental Material

MP4 File - PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph
Video showing the PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph

References

[1]
Paola F Antonietti, Nicola Farenga, Enrico Manuzzi, Gabriele Martinelli, and Luca Saverio. 2024. Agglomeration of polygonal grids using graph neural networks with applications to multigrid solvers. Computers & Mathematics with Applications, Vol. 154 (2024), 45--57.
[2]
Weijia Bei, Mingqiang Guo, and Ying Huang. 2019. A spatial adaptive algorithm framework for building pattern recognition using graph convolutional networks. Sensors, Vol. 19, 24 (2019), 5518.
[3]
Radu A Cosma, Lukas Knobel, Putri van der Linden, David M Knigge, and Erik J Bekkers. 2023. Geometric Superpixel Representations for Efficient Image Classification with Graph Neural Networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 109--118.
[4]
Alexander R Fabbri, Patrick Ng, Zhiguo Wang, Ramesh Nallapati, and Bing Xiang. 2020. Template-based question generation from retrieved sentences for improved unsupervised question answering. arXiv preprint arXiv:2004.11892 (2020).
[5]
Yu Feng, Frank Thiemann, and Monika Sester. 2019. Learning cartographic building generalization with deep convolutional neural networks. ISPRS International Journal of Geo-Information, Vol. 8, 6 (2019), 258.
[6]
David Gillsjö, Gabrielle Flood, and Kalle Åström. 2023. Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes. arXiv preprint arXiv:2306.12203 (2023).
[7]
Arnaud Gueze, Matthieu Ospici, Damien Rohmer, and Marie-Paule Cani. 2023. Floor Plan Reconstruction from Sparse Views: Combining Graph Neural Network with Constrained Diffusion. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 1583--1592.
[8]
Ehsan Hamzei, Martin Tomko, and Stephan Winter. 2022. Translating place-related questions to GeoSPARQL queries. In Proceedings of the ACM Web Conference 2022. 902--911.
[9]
Wenchong He, Zhe Jiang, Marcus Kriby, Yiqun Xie, Xiaowei Jia, Da Yan, and Yang Zhou. 2022. Quantifying and reducing registration uncertainty of spatial vector labels on earth imagery. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 554--564.
[10]
Xianjin He, Xinchang Zhang, and Qinchuan Xin. 2018. Recognition of building group patterns in topographic maps based on graph partitioning and random forest. ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 136 (2018), 26--40.
[11]
Ziniu Hu, Yuxiao Dong, Kuansan Wang, and Yizhou Sun. 2020. Heterogeneous graph transformer. In Proceedings of the web conference 2020. 2704--2710.
[12]
Chiyu Jiang, Dana Lansigan, Philip Marcus, Matthias Nießner, et al. 2019. Ddsl: Deep differentiable simplex layer for learning geometric signals. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 8769--8778.
[13]
Zhe Jiang, Wenchong He, Marcus Kirby, Sultan Asiri, and Da Yan. 2021. Weakly Supervised Spatial Deep Learning based on Imperfect Vector Labels with Registration Errors. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 767--775.
[14]
Zhe Jiang, Wenchong He, Marcus Stephen Kirby, Arpan Man Sainju, Shaowen Wang, Lawrence V Stanislawski, Ethan J Shavers, and E Lynn Usery. 2022. Weakly supervised spatial deep learning for earth image segmentation based on imperfect polyline labels. ACM Transactions on Intelligent Systems and Technology (TIST), Vol. 13, 2 (2022), 1--20.
[15]
Sergios-Anestis Kefalidis, Dharmen Punjani, Eleni Tsalapati, Konstantinos Plas, Mariangela Pollali, Michail Mitsios, Myrto Tsokanaridou, Manolis Koubarakis, and Pierre Maret. 2023. Benchmarking geospatial question answering engines using the dataset GeoQuestions1089. In International Semantic Web Conference. Springer, 266--284.
[16]
Werner Kuhn, Ehsan Hamzei, Martin Tomko, Stephan Winter, and Haonan Li. 2021. The semantics of place-related questions. Journal of Spatial Information Science 23 (2021), 157--168.
[17]
Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE, Vol. 86, 11 (1998), 2278--2324.
[18]
Muxingzi Li, Florent Lafarge, and Renaud Marlet. 2020. Approximating shapes in images with low-complexity polygons. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8633--8641.
[19]
Ding Ma, Zhigang Zhao, Ye Zheng, Renzhong Guo, and Wei Zhu. 2020. PolySimp: A tool for polygon simplification based on the underlying scaling hierarchy. ISPRS International Journal of Geo-Information, Vol. 9, 10 (2020), 594.
[20]
Gengchen Mai, Krzysztof Janowicz, Rui Zhu, Ling Cai, and Ni Lao. 2021. Geographic question answering: Challenges, uniqueness, classification, and future directions. AGILE: GIScience series, Vol. 2 (2021), 8.
[21]
Gengchen Mai, Chiyu Jiang, Weiwei Sun, Rui Zhu, Yao Xuan, Ling Cai, Krzysztof Janowicz, Stefano Ermon, and Ni Lao. 2023. Towards general-purpose representation learning of polygonal geometries. GeoInformatica, Vol. 27, 2 (2023), 289--340.
[22]
Wangshu Mu and Daoqin Tong. 2022. Computation of the distance between a polygon and a point in spatial analysis. International Journal of Geographical Information Science, Vol. 36, 8 (2022), 1575--1600.
[23]
Minh-Tri Pham, Yang Gao, Viet-Dung D Hoang, and Tat-Jen Cham. 2010. Fast polygonal integration and its application in extending haar-like features to improve object detection. In 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, 942--949.
[24]
Simon Scheider, Enkhbold Nyamsuren, Han Kruiger, and Haiqi Xu. 2021. Geo-analytical question-answering with GIS. International Journal of Digital Earth, Vol. 14, 1 (2021), 1--14.
[25]
Keith R Spangler, Paige Brochu, Amruta Nori-Sarma, Dennis Milechin, Michael Rickles, Brandeus Davis, Kimberly A Dukes, and Kevin J Lane. 2023. Calculating access to parks and other polygonal resources: a description of open-source methodologies. Spatial and spatio-temporal epidemiology, Vol. 47 (2023), 100606.
[26]
RH van't Veer, P Bloem, and EJA Folmer. 2019. Deep Learning for Classification Tasks on Geospatial Vector Polygons. stat, Vol. 1050 (2019), 11.
[27]
Lu Wang, Tinghua Ai, Dirk Burghardt, Yilang Shen, and Min Yang. 2023. A hexagon-based method for polygon generalization using morphological operators. International Journal of Geographical Information Science, Vol. 37, 1 (2023), 88--117.
[28]
Xiao Wang, Houye Ji, Chuan Shi, Bai Wang, Yanfang Ye, Peng Cui, and Philip S Yu. 2019. Heterogeneous graph attention network. In The world wide web conference. 2022--2032.
[29]
Xiongfeng Yan, Tinghua Ai, Min Yang, and Xiaohua Tong. 2021. Graph convolutional autoencoder model for the shape coding and cognition of buildings in maps. International Journal of Geographical Information Science, Vol. 35, 3 (2021), 490--512.
[30]
Xiongfeng Yan, Tinghua Ai, Min Yang, and Hongmei Yin. 2019. A graph convolutional neural network for classification of building patterns using spatial vector data. ISPRS journal of photogrammetry and remote sensing, Vol. 150 (2019), 259--273.
[31]
Dazhou Yu, Guangji Bai, Yun Li, and Liang Zhao. 2022. Deep Spatial Domain Generalization. In 2022 IEEE International Conference on Data Mining (ICDM). IEEE, 1293--1298.
[32]
Minxing Zhang, Dazhou Yu, Yun Li, and Liang Zhao. 2022. Deep geometric neural network for spatial interpolation. In Proceedings of the 30th International Conference on Advances in Geographic Information Systems. 1--4.
[33]
Minxing Zhang, Dazhou Yu, Yun Li, and Liang Zhao. 2023. Deep Spatial Prediction via Heterogeneous Multi-source Self-supervision. ACM Transactions on Spatial Algorithms and Systems, Vol. 9, 3 (2023), 1--26.
[34]
Zheng Zhang and Liang Zhao. 2021. Representation learning on spatial networks. Advances in Neural Information Processing Systems, Vol. 34 (2021), 2303--2318.
[35]
Wufan Zhao, Claudio Persello, and Alfred Stein. 2022. Extracting planar roof structures from very high resolution images using graph neural networks. ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 187 (2022), 34--45.
[36]
Yanfei Zhong, Yu Su, Siqi Wu, Zhendong Zheng, Ji Zhao, Ailong Ma, Qiqi Zhu, Richen Ye, Xiaoman Li, Petri Pellikka, et al. 2020. Open-source data-driven urban land-use mapping integrating point-line-polygon semantic objects: A case study of Chinese cities. Remote Sensing of Environment, Vol. 247 (2020), 111838.
[37]
Stefano Zorzi, Shabab Bazrafkan, Stefan Habenschuss, and Friedrich Fraundorfer. 2022. Polyworld: Polygonal building extraction with graph neural networks in satellite images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1848--1857.

Cited By

View all
  • (2024)SpaGAN: A spatially-aware generative adversarial network for building generalization in image mapsInternational Journal of Applied Earth Observation and Geoinformation10.1016/j.jag.2024.104236135(104236)Online publication date: Dec-2024

Index Terms

  1. PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph
            Index terms have been assigned to the content through auto-classification.

            Recommendations

            Comments

            Please enable JavaScript to view thecomments powered by Disqus.

            Information & Contributors

            Information

            Published In

            cover image ACM Conferences
            KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
            August 2024
            6901 pages
            ISBN:9798400704901
            DOI:10.1145/3637528
            Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

            Sponsors

            Publisher

            Association for Computing Machinery

            New York, NY, United States

            Publication History

            Published: 24 August 2024

            Permissions

            Request permissions for this article.

            Check for updates

            Author Tags

            1. heterogeneous graph neural networks
            2. multipolygon
            3. polygonal geometry
            4. representation learning
            5. visibility graph

            Qualifiers

            • Research-article

            Funding Sources

            Conference

            KDD '24
            Sponsor:

            Acceptance Rates

            Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

            Upcoming Conference

            KDD '25

            Contributors

            Other Metrics

            Bibliometrics & Citations

            Bibliometrics

            Article Metrics

            • Downloads (Last 12 months)382
            • Downloads (Last 6 weeks)104
            Reflects downloads up to 21 Dec 2024

            Other Metrics

            Citations

            Cited By

            View all
            • (2024)SpaGAN: A spatially-aware generative adversarial network for building generalization in image mapsInternational Journal of Applied Earth Observation and Geoinformation10.1016/j.jag.2024.104236135(104236)Online publication date: Dec-2024

            View Options

            View options

            PDF

            View or Download as a PDF file.

            PDF

            eReader

            View online with eReader.

            eReader

            Login options

            Media

            Figures

            Other

            Tables

            Share

            Share

            Share this Publication link

            Share on social media