摘要
图神经网络作为一种新兴的深度学习方法,能够有效建模和表示图结构数据,在各种图学习任务中表现优异。然而,现有的图神经网络大多聚焦于单一通道图卷积,未能充分利用现实世界图数据中丰富多样的关系信息。为深入挖掘图数据中的多关系特征并提升图神经网络的建模能力,提出了一种基于Weisfeiler-Lehman(WL)图核的多通道图Kolmogorov-Arnold网络(KMCGKN)。该方法通过提取节点领域子图并借助WL图核方法构建特征图,且将原本图卷积层中的特征变换函数替换成Kolmogorov-Arnold网络,然后利用两个图卷积网络通道分别学习不同关系图的特性,从而得到图的特征编码和结构编码。同时,通过多视图损失确保通道间的差异性,缓解了深层模型的过拟合问题。在6个节点分类公开数据集上进行了评估,实验结果表明,KMCGKN方法在节点分类任务上的性能优于单通道GCN及其他基准模型,有效提升了图神经网络的建模与表示能力。
As an emerging deep learning method,graph neural networks have demonstrated powerful capabilities in modeling and representing graph structure data in various graph learning tasks.However,most existing graph neural networks focus on single-channel graph convolution and fail to make full use of the rich and diverse relationship information in real-world graph data.To deeply mine multi-relational features in graph data and enhance the modeling capabilities of graph neural networks,this paper proposes a multi-channel graph Kolmogorov-Arnold network based on the Weisfeiler-Lehman graph kernel(KMCGKN).This method extracts the node domain subgraph and constructs the feature map with the help of the Weisfeiler-Lehman graph kernel method,and replaces the feature transformation function in the original graph convolution layer with the Kolmogorov-Arnold network.Then,two graph convolution network channels learn the characteristics of different relationship graphs respectively,thereby obtaining the feature encoding and structural encoding of the graph.At the same time,the multi-view loss ensures the diffe-rence between channels,which alleviates the overfitting problem of deep models.The KMCGKN method is evaluated on six node classification public data sets.Experimental results show that its performance in node classification tasks is better than single-channel GCN and other benchmark models,effectively improving the model modeling and representation capabilities.
作者
王静红
李鹏超
米据生
王威
WANG Jinghong;LI Pengchao;MI Jusheng;and WANG Wei(College of Computer and Cyber Security,Hebei Normal University,Shijiazhuang 050024,China;College of Artificial Intelligence,Hebei University of Engineering Technology,Shijiazhuang 050020,China;State Key Laboratory of Cognitive Intelligence,University of Science and Technology of China,Hefei 230088,China;Hebei Provincial Key Laboratory of Network and Information Security,Shijiazhuang 050024,China;Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics&Data Security,Shijiazhuang 050024,China;School of Mathematical Sciences,Hebei Normal University,Shijiazhuang 050024,China)
出处
《计算机科学》
北大核心
2026年第4期224-234,共11页
Computer Science
基金
河北省自然科学基金(F2024205028)
河北省研究生创新资助项目(CXZZSS2025049)
河北师范大学科技类科研基金(L2023J05,L2024C05)
河北师范大学重点发展基金(L2024ZD06)
认知智能全国重点实验室开放课题(COGOS-2025HE07)。
