计算机科学 ›› 2026, Vol. 53 ›› Issue (4): 224-234.doi: 10.11896/jsjkx.250600033
王静红1,2,3,4, 李鹏超1,3,4,5, 米据生4,5,6, 王威1,4,5
WANG Jinghong1,2,3,4, LI Pengchao1,3,4,5, MI Jusheng4,5,6, WANG Wei1,4,5
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。
中图分类号:
| [1]GLIGORIJEVIC V,BAROT M,BONNEAU R.deepNF:deepnetwork fusion for protein function prediction[J].Bioinforma-tics,2018,34(22):3873-3881. [2]FARAHANI R Z,MIANDOABCHI E,SZETO W Y,et al.A review of urban transportation network design problems[J].European journal of operational research,2013,229(2):281-302. [3]XIAO S,WANG S,DAI Y,et al.Graph neural networks in node classification:survey and evaluation[J].Machine Vision and Applications,2022,33(1):4. [4]WANG C,PAN S,CELINA P Y,et al.Deep neighbor-awareembedding for node clustering in attributed graphs[J].Pattern Recognition,2022,122:108230. [5]ZHANG M,CHEN Y.Link prediction based on graph neural networks[C]//Proceedings of the 32nd International Confe-rence on Neural Information Processing Systems.2018:5171-5181. [6]CHEN X,JIA S,XIANG Y.A review:Knowledge reasoning over knowledge graph[J].Expert Systems with Applications,2020,141:112948. [7]YING R,HE R,CHEN K,et al.Graph convolutional neural net-works for web-scale recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:974-983. [8]SHERVASHIDZE N,SCHWEITZER P,VAN LEEUWEN EJ,et al.Weisfeiler-lehman graph kernels[J].Journal of Machine Learning Research,2011,12(9):2539-2561. [9]VASWANI A,SHAZEER N,PARMAER N,et al.Attention is all you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010. [10]LIU Z,WANG Y,VAIDYA S,et al.Kan:Kolmogorov-arnold networks[J].arXiv:2404.19756,2024. [11]BRAUN J,GRIEBEL M.On a constructive proof of Kolmogo-rov’s superposition theorem[J].Constructive Approximation,2009,30:653-675. [12]LAI M J,SHEN Z.The kolmogorov superposition theorem can break the curse of dimensionality when approximating high dimensional functions[J].arXiv:2112.09963,2021. [13]SU Z,CHEN M,AI J,et al.Research on Recommendation Algo-rithm Based on Kolmogorov-Arnold Network-driven Scoring and Review Fusion[J].Journal of Chinese Computer Systems,2025,46(11):2600-2609. [14]LIN R,DU S,WANG S,et al.Multi-channel augmented graph embedding convolutional network for multi-view clustering[J].IEEE Transactions on Network Science and Engineering,2023,10(4):2239-2249. [15]ZHU X,LI C,GUO J,et al.CNIM-GCN:consensus neighbor interaction-based multi-channel graph convolutional networks[J].Expert Systems with Applications,2023,226:120178. [16]ZHAI R,ZHANG L,WANG Y,et al.A multi-channel attention graph convolutional neural network for node classification[J].The Journal of Supercomputing,2023,79(4):3561-3579. [17]CHAO H,CAO Y,LIU Y.Multi-channel EEG emotion recognition through residual graph attention neural network[J].Frontiers in Neuroscience,2023,17:1135850. [18]LI J,LU G,WU Z,et al.Multi-view representation model based on graph autoencoder[J].Information Sciences,2023,632:439-453. [19]WU Z,LIN X,LIN Z,et al.Interpretable graph convolutional network for multi-view semi-supervised learning[J].IEEE Transactions on Multimedia,2023,25:8593-8606. [20]CHEN Y,WU Z,CHEN Z,et al.Joint learning of feature and topology for multi-view graph convolutional network[J].Neural Networks,2023,168:161-170. [21]SHAWE-TAYLOR J,CRISTIANINI N.Kernel methods forpattern analysis[M].Cambridge:Cambridge University Press,2004. [22]KANG U,TONG H,SUN J.Fast random walk graph kernel[C]//Proceedings of the 2012 SIAM International Conference on Data Mining.2012:828-838. [23]BORGWARDT K M,KRIGEL H P.Shortest-path kernels on graphs[C]//Fifth IEEE International Conference on Data Mi-ning(ICDM’05).IEEE,2005. [24]SHERVASHIDZE N,VISHWANATHAN S V N,PETRI T,et al.Efficient graphlet kernels for large graph comparison[C]//Artificial Intelligence and Statistics.PMLR,2009:488-495. [25]CHEN D,JACOB L,MAIRAL J.Convolutional kernel networks for graph-structured data[C]//International Conference on Machine Learning.PMLR,2020:1576-1586. [26]NAMATA G,LONDON B,GETOOR L,et al.Query-driven active surveying for collective classification[C]//10th Internatio-nal Workshop on Mining and Learning with Graphs.2012. [27]PEI H,WEI B,CHANG K C C,et al.Geom-gcn:Geometric graph convolutional networks[J].arXiv:2002.05287,2020. [28]TANG J,SUN J,WANG C,et al.Social influence analysis in large-scale networks[C]//Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mi-ning.2009:807-816. [29]GROVER A,LESKOVEC J.node2vec:Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mi-ning.2016:855-864. [30]PEROZZI B,AL-RFOU R,SKIENA S.Deepwalk:Online lear-ning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2014:701-710. [31]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016. [32]VELICKOVIC P,CUCURULL G,CASANOVA A,et al.Graph attention networks[J].arXiv:1710.10903,2017. [33]HAMILTON W,YING Z,LESKOVEC J.Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:1025-1035. [34]WU F,SOUZA A,ZHANG T,et al.Simplifying graph convolutional networks[C]//International Conference on Machine Learning.2019:6861-6871. [35]ZHU J,ROSSI R A,RAO A,et al.Graph Neural Networks with Heterophily[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:11168-11176 [36]WANG T,JIN D,WANG R,et al.Powerful graph convolutional networks with adaptive propagation mechanism for homophily and heterophily[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022:4210-4218. [37]GAO H,JI S.Graph U-Nets[C]//International Conference on Machine Learning.PMLR,2019:2083-2092. [38]WU J,CHEN X,XU K,et al.Structural entropy guided graph hierarchical pooling[C]//International Conference on Machine Learning.PMLR,2022:24017-24030. |
| [1] | 高泰, 任艳璋, 王会青, 李颖, 王彬. KGMamba:基于Kolmogorov-Arnold网络优化图卷积网络和Mamba的基因调控网络预测模型 KGMamba:Gene Regulatory Network Prediction Model Based on Kolmogorov-Arnold Network Optimizing Graph Convolutional Network and Mamba 计算机科学, 2026, 53(4): 101-111. https://doi.org/10.11896/jsjkx.250500097 |
| [2] | 王静红, 李鹏超, 王熙照, 张自立. 基于KAN的双通道图神经网络 Dual-channel Graph Neural Network Based on KAN 计算机科学, 2026, 53(3): 188-196. https://doi.org/10.11896/jsjkx.250600067 |
| [3] | 丁艳, 丁红发, 喻沐然, 蒋合领. 图神经网络后门攻击与防御综述 Survey of Backdoor Attacks and Defenses on Graph Neural Network 计算机科学, 2026, 53(3): 1-22. https://doi.org/10.11896/jsjkx.250700093 |
| [4] | 赵正彪, 卢涵宇, 丁红发. 基于节点影响力的图遗忘学习近似最差遗忘集构造算法 Node-influence Based Construction Algorithm of Approximate Worst-case Forgetting Set for Graph Unlearning 计算机科学, 2026, 53(3): 64-77. https://doi.org/10.11896/jsjkx.250700094 |
| [5] | 李诚宇, 黄可, 张锐恒, 陈伟. 基于异构图注意力网络的智能合约漏洞检测方法 Heterogeneous Graph Attention Network-based Approach for Smart Contract Vulnerability Detection 计算机科学, 2026, 53(2): 423-430. https://doi.org/10.11896/jsjkx.241200144 |
| [6] | 王新喻, 宋小民, 郑慧明, 彭德中, 陈杰. 融合对比学习的掩码图自编码器 Contrastive Learning-based Masked Graph Autoencoder 计算机科学, 2026, 53(2): 145-151. https://doi.org/10.11896/jsjkx.250100155 |
| [7] | 翟洁, 陈乐旋, 庞智玉. 基于图神经网络的学业表现预测方法研究综述 Survey on Graph Neural Network-based Methods for Academic Performance Prediction 计算机科学, 2026, 53(2): 16-30. https://doi.org/10.11896/jsjkx.250800001 |
| [8] | 杨明, 贺超波, 杨佳琦. 基于方向感知孪生网络的知识概念先序关系预测方法 Direction-aware Siamese Network for Knowledge Concept Prerequisite Relation Prediction 计算机科学, 2026, 53(2): 39-47. https://doi.org/10.11896/jsjkx.250600005 |
| [9] | 刘宏鉴, 邹丹平, 李萍. 基于图注意力交互的行人轨迹预测方法 Pedestrian Trajectory Prediction Method Based on Graph Attention Interaction 计算机科学, 2026, 53(1): 97-103. https://doi.org/10.11896/jsjkx.250300132 |
| [10] | 李亚茹, 王倩倩, 车超, 朱德恒. 基于药物子结构与蛋白质三维图信息的化合物-蛋白质相互作用预测 Graph-based Compound-Protein Interaction Prediction with Drug Substructures and Protein 3D Information 计算机科学, 2025, 52(9): 71-79. https://doi.org/10.11896/jsjkx.250100116 |
| [11] | 吴晗禹, 刘天赐, 矫拓成, 车超. 基于动态超图与药物处方信息融合的时序健康事件预测 DHMP:Dynamic Hypergraph-enhanced Medication-aware Model for Temporal Health EventPrediction 计算机科学, 2025, 52(9): 88-95. https://doi.org/10.11896/jsjkx.250300012 |
| [12] | 苏世玉, 于炯, 李姝, 酒世承. 基于双重分类和重建的跨域图异常检测 Cross-domain Graph Anomaly Detection Via Dual Classification and Reconstruction 计算机科学, 2025, 52(8): 374-384. https://doi.org/10.11896/jsjkx.241000140 |
| [13] | 唐博源, 李琦. 时空图神经网络在PM2.5浓度预测中的应用综述 Review on Application of Spatial-Temporal Graph Neural Network in PM2.5 ConcentrationForecasting 计算机科学, 2025, 52(8): 71-85. https://doi.org/10.11896/jsjkx.240700153 |
| [14] | 王沛, 杨希洪, 管仁祥, 祝恩. 基于动态阈值伪标签筛选的深度图对比聚类算法 Deep Graph Contrastive Clustering Algorithm Based on Dynamic Threshold Pseudo-label Selection 计算机科学, 2025, 52(8): 100-108. https://doi.org/10.11896/jsjkx.240700112 |
| [15] | 郭虎升, 张旭飞, 孙玉杰, 王文剑. 随时间持续演化的流图神经网络 Continuously Evolution Streaming Graph Neural Network 计算机科学, 2025, 52(8): 118-126. https://doi.org/10.11896/jsjkx.241000186 |
|
||
首页