Reasoning over higher-order qualitative spatial relations via spatially explicit neural network

This file contains the data and code to reproduce the results from the paper "Reasoning over higher-order qualitative spatial relations via spatially explicit neural network". Instructions of running the code can be found at README.txt <br> Abstract of the paper: Qualitative spatial reasoning has been a core research topic in GIScience and AI for decades. It has been adopted in a wide range of applications such as wayfinding, question answering, and robotics. Most developed spatial inference engines use symbolic representation and reasoning, which focuses on small and densely connected data sets, and struggles to deal with noise and vagueness. However, with more sensors becoming available, reasoning over spatial relations on large-scale and noisy geospatial data sets requires more robust alternatives. This paper, therefore, proposes a subsymbolic approach using neural networks to facilitate qualitative spatial reasoning. More specifically, we focus on higher-order spatial relations as those have been largely ignored due to the binary nature of the underlying representations, e.g., knowledge graphs. We specifically explore the use of neural networks to reason over ternary projective relations such as between. We consider multiple types of spatial constraint, including higher-order relatedness and the conceptual neighborhood of ternary projective relations to make the proposed model spatially explicit. We introduce evaluating results demonstrating that the proposed spatially explicit method substantially outperforms existing baseline by about 20%.

本文件包含复现论文《通过空间显式神经网络进行高阶定性空间关系推理》（Reasoning over higher-order qualitative spatial relations via spatially explicit neural network）实验结果所需的数据与代码。代码运行说明详见README.txt文件。

论文摘要：定性空间推理数十年来一直是地理信息科学（GIScience）与人工智能（AI）领域的核心研究课题。其已被广泛应用于路径规划、问答系统、机器人学等诸多场景。现有多数空间推理引擎采用符号化表示与推理范式，这类方法通常仅适用于小型且紧密连接的数据集，且难以处理噪声与模糊性问题。然而，随着各类传感器的普及，针对大规模含噪地理空间数据集的空间关系推理亟需更为鲁棒的解决方案。为此，本文提出一种基于神经网络的亚符号（subsymbolic）方法以支撑定性空间推理任务。具体而言，本文聚焦高阶空间关系——这类关系因底层表示（如知识图谱（knowledge graphs））的二元性本质而长期被忽视。我们针对性地探究了利用神经网络对‘between’这类三元射影关系（ternary projective relations）开展推理的方法。为使所提模型具备空间显式性，我们引入了多种空间约束，涵盖高阶关联性与三元射影关系的概念邻域（conceptual neighborhood）。本文所呈现的评估结果表明，所提出的空间显式方法相较现有基准模型性能提升约20%，优势显著。