{"ID":2826590,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.18826","arxiv_id":"2512.18826","title":"Hyperbolic Graph Embeddings: a Survey and an Evaluation on Anomaly Detection","abstract":"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.","short_abstract":"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{\\(\\mathc...","url_abs":"https://arxiv.org/abs/2512.18826","url_pdf":"https://arxiv.org/pdf/2512.18826v1","authors":"[\"Souhail Abdelmouaiz Sadat\",\"Mohamed Yacine Touahria Miliani\",\"Khadidja Hab El Hames\",\"Hamida Seba\",\"Mohammed Haddad\"]","published":"2025-12-21T17:19:29Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Variational Autoencoder\"]","has_code":false}