A novel architecture and training strategy for graph neural networks (GNN). The proposed architecture, named as Autoencoder-Aided GNN (AA-GNN), compresses the convolutional features at multiple hidden ...

In the context of these analyses, Graph Neural Networks (GNNs) emerge as powerful tools for considering the proximity of sample neighbors in anomaly detection and data classification, particularly ...

Still, most of the current graph neural networks are based on supervised learning or semi-supervised learning, which often relies on the true labels of the given samples as auxiliary information. To ...

Graph Autoencoder Networks. The wide application of autoencoder (AE) and its variants in the field of unsupervised learning has led to an increasing number of AE-based graph generation models. Sparse ...

In this paper, a novel local anomaly detection model DAGNN is proposed, which incorporates a graph neural network to better aggregate neighbors' distance information of each sample for forming its ...

Predicting potential microbe-disease associations with graph attention autoencoder, positive-unlabeled learning, and deep neural network Lihong Peng 1,2 † Liangliang Huang 1 † Geng Tian 3 Yan Wu 3 ...

Graph neural networks are very powerful tools. They have already found powerful applications in domains such as route planning, fraud detection, network optimization, and drug research.