Hyperbolic Graph Embeddings: a Survey and an Evaluation on Anomaly Detection
This work addresses the problem of anomaly detection in complex graph data for researchers and practitioners, but it is incremental as it surveys and evaluates existing methods rather than introducing new ones.
This survey reviews hyperbolic graph embedding models and evaluates them on anomaly detection, showing that hyperbolic methods like \(\mathcal{P}\)-VAE achieve an F1-score of 94% on the Elliptic dataset, outperforming Euclidean methods.
This survey reviews hyperbolic graph embedding models, and evaluate them on anomaly detection, highlighting their advantages over Euclidean methods in capturing complex structures. Evaluating models like \textit{HGCAE}, \textit{\(\mathcal{P}\)-VAE}, and \textit{HGCN} demonstrates high performance, with \textit{\(\mathcal{P}\)-VAE} achieving an F1-score of 94\% on the \textit{Elliptic} dataset and \textit{HGCAE} scoring 80\% on \textit{Cora}. In contrast, Euclidean methods like \textit{DOMINANT} and \textit{GraphSage} struggle with complex data. The study emphasizes the potential of hyperbolic spaces for improving anomaly detection, and provides an open-source library to foster further research in this field.