高级检索
    徐立祥, 葛伟, 陈恩红, 罗斌. 基于图核同构网络的图分类方法[J]. 计算机研究与发展. DOI: 10.7544/issn1000-1239.202221004
    引用本文: 徐立祥, 葛伟, 陈恩红, 罗斌. 基于图核同构网络的图分类方法[J]. 计算机研究与发展. DOI: 10.7544/issn1000-1239.202221004
    Xu Lixiang, Ge Wei, Chen Enhong, Luo Bin. Graph Classification Method Based on Graph Kernel Homomorphic Network[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202221004
    Citation: Xu Lixiang, Ge Wei, Chen Enhong, Luo Bin. Graph Classification Method Based on Graph Kernel Homomorphic Network[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202221004

    基于图核同构网络的图分类方法

    Graph Classification Method Based on Graph Kernel Homomorphic Network

    • 摘要: 图表示学习已成为图深度学习领域的一个研究热点. 大多数图神经网络存在过平滑现象,这类方法重点关注图节点特征,对图的结构特征关注度不高. 为了提升对图结构特征的表征能力,提出了一种基于图核同构网络的图分类方法,即KerGIN. 该方法首先通过图同构网络(GIN)对图进行节点特征编码,并使用图核方法对图进行结构编码,进一步利用Nyström方法降低图核矩阵的维度,其次借助MLP将图核矩阵与图特征矩阵对齐,通过注意力机制将图的特征编码和结构编码进行自适应加权融合,进而得到图的最终特征表示,提升了图结构特征信息的表达能力. 最后在7个公开的图分类数据集上对模型进行了实验评估:与现有图表示模型相比,KerGIN模型能够在图分类精度上有较大幅度提升,它可以增强GIN对图结构特征信息的表达能力.

       

      Abstract: Graph representation learning has become a research hotspot in the field of graph deep learning. Most graph neural networks suffer from oversmoothing, and these methods focus on graph node features and pay little attention to the structural features of graphs. In order to improve the representation of graph structural features, this paper proposes a graph classification method based on graph kernel homomorphic network, namely KerGIN. The method first encodes the node features of the graph through Graph Isomorphism Network(GIN), and then uses the graph kernel method to encode the graph structure. The Nyström method is further used to reduce the dimension of the graph kernel matrix. The graph kernel matrix is aligned with the graph feature matrix with MLP, and the feature encoding and structure encoding of the graph are adaptively weighted and fused through the attention mechanism to obtain the final feature representation of the graph, which enhances the ability to express the structural feature information of the graph. Finally, the model is experimentally evaluated on seven publicly available graph classification datasets: compared with the existing graph representation models, the KerGIN model is able to improve the graph classification accuracy substantially, and it can enhance the ability of GIN to represent the graph structural feature information.

       

    /

    返回文章
    返回