Methods for constructing graph neural networks

Discusses an approach to classifying graph neural networks in terms of basic concepts. In addition, the fundamentals of convolutional graph neural networks, Graph attentional neural networks, recurrent graph neural networks, graph automatic encoders, and spatial-temporal graph neural networks are discussed. On the example of Cora dataset, a comparison of neural network models presented in TensorFlow, PyTorch libraries, as well as the model of graph neural network of attention for the task of classification of nodes of the knowledge graph, is carried out. The efficiency of using graph attention networks to solve the problem of graph node classification is shown.

Authors: M. V. Murzin, I. A. Kulikov, N. A. Zhukova

Direction: Informatics, Computer Technologies And Control

Keywords: knowledge graphs, graph neural networks, graph node classification

---

View full article