A Generative Bayesian Graph Attention Network for Semi-supervised Classification on Scarce Data

Sun, Zhongtian; Harit, Anoushka; Yu, Jialin; Cristea, Alexandra; Al Moubayed, Noura

Abstract

This research focuses on semi-supervised classification tasks, specifically for graph-structured data under datascarce situations. It is known that the performance of conventional supervised graph convolutional models is mediocre at classification tasks, when only a small fraction of the labeled nodes are given. Additionally, most existing graph neural network models often ignore the noise in graph generation and consider all the relations between objects as genuine ground-truth. Hence, the missing edges may not be considered, while other spurious edges are included. Addressing those challenges, we propose a Bayesian Graph Attention model which utilizes a generative model to randomly generate the observed graph. The method infers the joint posterior distribution of node labels and graph structure, by combining the Mixed-Membership Stochastic Block Model with the Graph Attention Model. We adopt a variety of approximation methods to estimate the Bayesian posterior distribution of the missing labels. The proposed method is comprehensively evaluated on three graph-based deep learning benchmark data sets. The experimental results demonstrate a competitive performance of our proposed model BGAT against the current state of the art models when there are few labels available (the highest improvement is 5%), for semi-supervised node classification tasks.

Citation

Sun, Z., Harit, A., Yu, J., Cristea, A., & Al Moubayed, N. (2021, July). A Generative Bayesian Graph Attention Network for Semi-supervised Classification on Scarce Data. Presented at IEEE International Joint Conference on Neural Network (IJCNN2021), Virtual

• Presentation Conference Type: Conference Paper (published)
• Conference Name: IEEE International Joint Conference on Neural Network (IJCNN2021)
• Start Date: Jul 18, 2021
• End Date: Jul 22, 2021
• Acceptance Date: Jul 1, 2021
• Online Publication Date: Sep 20, 2021
• Publication Date: 2021
• Deposit Date: Jul 20, 2021
• Publicly Available Date: Jul 23, 2021
• Series ISSN: 2161-4393,2161-4407
• DOI: https://doi.org/10.1109/ijcnn52387.2021.9533981
• Public URL: https://durham-repository.worktribe.com/output/1140645