Meta-path convolution based heterogeneous graph neural network algorithm
In the multilayer graph convolution calculation,each node is usually represented as a single vector,which makes the high-order graph convolution layer unable to distinguish the information of different relationships and se-quences,resulting in the loss of information in the transmission process.To solve this problem,a heterogeneous graph neural network algorithm based on meta-path convolution was proposed.Firstly,the feature transformation was used to adaptively adjust the node features.Secondly,the high-order indirect relationship between the nodes was mined by convolution within the meta-path to capture the interaction between the target node and other types of nodes under the element path.Finally,the reciprocity between semantics was explored through the self-attention mechanism,and the features from different meta-paths were fused.Extensive experiments were carried out on ACM,IMDB and DBLP da-tasets,and compared with the current mainstream algorithms.The experimental results show that the average increase of Macro-F1 in the node classification task is 0.5%～3.5%,and the ARI value in the node clustering task is increased by 1%～3%,which proves that the algorithm is effective and feasible.
万方数据
维普
