Abstract
As a widely studied model in the machine learning and data processing society, graph convolutional network reveals its advantage in non-grid data processing. However, existing graph convolutional networks generally assume that the node features can be fully observed. This may violate the fact that many real applications come with only the pairwise relationships and the corresponding node features are unavailable. In this paper, a novel graph convolutional network model based on Bayesian framework is proposed to handle the graph node classification task without relying on node features. First, we equip the graph node with the pseudo-features generated from the stochastic process. Then, a hidden space structure preservation term is proposed and embedded into the generation process to maintain the independent and identically distributed property between the training and testing dataset. Although the model inference is challenging, we derive an efficient training and predication algorithm using variational inference. Experiments on different datasets demonstrate the proposed graph convolutional networks can significantly outperform traditional methods, achieving an average performance improvement of 9%.
Funder
National Natural Science Foundation of China
Natural Science Foundation of Zhejiang Province
research project of College of Science and Technology, Ningbo University
Publisher
Public Library of Science (PLoS)
Reference67 articles.
1. Deep HT: A deep neural network for diagnose on MR images of tumors of the hand;X Hu;PLOS ONE,2020
2. PharmaNet: Pharmaceutical discovery with deep recurrent neural networks;P Ruiz Puentes;PLOS ONE,2021
3. Law MT, Urtasun R, Zemel RS. Deep spectral clustering learning. In: International Conference on Machine Learning; 2017. p. 1985–1994.
4. Gatys LA, Ecker AS, Bethge M. Image Style Transfer Using Convolutional Neural Networks. In: Computer Vision & Pattern Recognition; 2016.
5. GraphDTA: predicting drug–target binding affinity with graph neural networks;T Nguyen;Bioinformatics,2021