基于混合特征建模的图卷积网络方法

对于网络中拥有的复杂信息，需要更多的方式抽取其中的有用信息，但现有的单特征图神经网络（GNN）无法完整地刻画网络中的相关特性。针对该问题，提出基于混合特征的图卷积网络（HDGCN）方法。首先，通过图卷积网络（GCN）得到节点的结构特征向量和语义特征向量；然后，通过改进基于注意力机制或门控机制的聚合函数选择性地聚合语义网络节点的特征，增强节点的特征表达能力；最后，通过一种基于双通道图卷积网络的融合机制得到节点的混合特征向量，将节点的结构特征和语义特征联合建模，使特征之间互相补充，提升该方法在后续各种机器学习任务上的表现。在CiteSeer、DBLP和SDBLP三个数据集上进行实验的结果表明，与基于结构特征训练的GCN相比，HDGCN在训练集比例为20%、40%、60%、80%时的Micro?F1值平均分别提升了2.43、2.14、1.86和2.13个百分点，Macro?F1值平均分别提升了1.38、0.33、1.06和0.86个百分点。用拼接或平均值作为融合策略时，准确率相差不超过0.5个百分点，可见拼接和平均值均可作为融合策略。HDGCN在节点分类和聚类任务上的准确率高于单纯使用结构或语义网络训练的模型，并且在输出维度为64、学习率为0.001、2层图卷积层和128维注意力向量时的效果最好。

Graph convolutional network method based on hybrid feature modeling

For the complex information contained in the network， more ways are needed to extract useful information from it， but the relevant characteristics in the network cannot be completely described by the existing single?feature Graph Neural Network （GNN）. To resolve the above problems， a Hybrid feature?based Dual Graph Convolutional Network （HDGCN） was proposed. Firstly， the structure feature vectors and semantic feature vectors of nodes were obtained by Graph Convolutional Network （GCN）. Secondly， the features of nodes were aggregated selectively so that the feature expression ability of nodes was enhanced by the aggregation function based on attention mechanism or gating mechanism. Finally， the hybrid feature vectors of nodes were gained by the fusion mechanism based on a feasible dual?channel GCN， and the structure features and semantic features of nodes were modeled jointly to make the features be supplement for each other and promote the method's performance on subsequent machine learning tasks. Verification was performed on the datasets CiteSeer， DBLP （DataBase systems and Logic Programming） and SDBLP （Simplified DataBase systems and Logic Programming）. Experimental results show that compared with the graph convolutional network model based on structure feature training， the dual channel graph convolutional network model based on hybrid feature training has the average value of Micro?F1 increased by 2.43， 2.14， 1.86 and 2.13 percentage points respectively， and the average value of Macro?F1 increased by 1.38， 0.33， 1.06 and 0.86 percentage points respectively when the training set proportion is 20%， 40%， 60% and 80%. The difference in accuracy is no more than 0.5 percentage points when using concat or mean as the fusion strategy， which shows that both concat and mean can be used as the fusion strategy. HDGCN has higher accuracy on node classification and clustering tasks than models trained by structure or semantic network alone， and has the best results when the output dimension is 64， the learning rate is 0.001， the graph convolutional layer number is 2 and the attention vector dimension is 128.