arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.00742cs.CVcs.LG
收藏

PolygonGNN:基于异构可见性图的多边形几何表示学习

PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph

Emory University(埃默里大学)

Dazhou Yu, Yuntong Hu, Yun Li, Liang Zhao

AI总结:

本文提出PolygonGNN框架,通过异构可见性图、生成树采样和旋转-平移不变表示,解决多面体几何表示学习中内部及多边形间关系建模不足的问题,并在五个数据集上验证其有效性。

摘要:

多边形表示学习对于多种应用至关重要,涵盖形状编码、建筑模式分类和地理问答等任务。尽管近年来该领域取得了显著进展,但大部分研究聚焦于单个多边形,忽视了多面体中固有的内部及多边形间复杂关系。为弥补这一不足,本研究引入了一个专为学习多边形几何(尤其是多面体)表示而设计的综合框架。我们方法的核心是引入异构可见性图,它无缝整合了内部及多边形间关系。为提高计算效率并减少图冗余,我们实现了一种异构生成树采样方法。此外,我们设计了一种旋转-平移不变的几何表示,确保在多种场景下具有更广泛的适用性。最后,我们提出了Multipolygon-GNN,这是一种专门利用可见性图中固有的空间和语义异构性的新型模型。在五个真实世界和合成数据集上的实验表明,该模型能够为多边形几何捕获具有信息量的表示。代码和数据可在https://github.com/dyu62/PolyGNN获取。

英文摘要:

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 \href{https://github.com/dyu62/PolyGNN}{$github.com/dyu62/PolyGNN$}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑