Outlier detection variational autoencoder

Anomaly detection in graph-based data is an emerging field in machine learning with many relevant applications. Although some algorithms have been developed, current models lack consistency on real-world data and often have problems with overfitting. The paper presents a new model to address these challenges. The model is a combination of graph neural network layers in a variational autoencoder framework. The graph convolution layers learn complex relationships between the node attributes, while also taking the graph structure into account. By using the variational autoencoder framework, the model is less likely to have overfitting problems. The model outperformed existing models on four of five real-world datasets with organic outliers, two out of three real-world datasets with synthetic outliers, and was the second best on the other two datasets. The model demonstrates the potential to combine the variational autoencoder architecture with graph convolution layers in graph deep learning tasks on outlier detection.