多尺度特征融合的图嵌入方法

Graph embedding method integrated with multiscale features

针对结构模式识别领域中通用图嵌入方法缺乏且计算复杂度较高的问题,基于空间句法理论提出一种融合多尺度特征的图嵌入方法。通过提取图的节点数、边数和智能度等全局特征、节点拓扑特征、边领域特征差异度和边拓扑特征差异度等局部特征和节点与边上的数值属性和符号属性等细节特征,利用多尺度直方图统计的方法构造描述图特征的特征向量,以此将桥梁将结构模式识别问题转化为统计模式识别问题,进而借助支持向量机(SVM)实现图的分类识别。实验结果表明,所提出的图嵌入方法在不同的图数据集上均具有较高的分类识别率。与其他图嵌入方法相比,该方法对图的拓扑表达能力强,并且可融合图的领域方面的非拓扑特征,通用性较好,计算复杂度较低。

In the domain of structural pattern recognition, the existing graph embedding methods lack versatility and have high computation complexity. A new graph embedding method integrated with muhiseale features based on space syntax theory was proposed to solve this problem. This paper extracted the global, local and detail features to construct feature vector depicting the graph feature by muhiscale histogram. The global features included vertex number, edge number, and intelligible degree. The local features referred to node topological feature, edge domain feature＇s dissimilarity and edge topological feature＇s dissimilarity. The detail features comprised numerical and symbolic attributes on vertex and edge. In this way, the structural pattern recognition was converted into statistical pattern recognition, thus Support Vector Machine （SVM） could be applied to achieve graph classification. The experimental results show that the proposed graph embedding method can achieve higher classifying accuracy in different graph datasets. Compared with other graph embedding methods, the proposed method can adequately render the graph＇s topology, merge the non-topological features in terms of the graph＇s domain property, and it has a favorable universality and low computation complexity.