Poster
in
Workshop: Structured Probabilistic Inference and Generative Modeling
Anomaly Detection in Networks via Score-Based Generative Models
Dmitrii Gavrilev · Evgeny Burnaev
Keywords: [ Graph Neural Networks ] [ score-based generative models ] [ Anomaly detection ] [ Diffusion Models ]
Node outlier detection in attributed graphs is a challenging problem for which there is no method that would work well across different datasets. Motivated by the state-of-the-art results of score-based models in graph generative modeling, we propose to incorporate them into the aforementioned problem. Our method achieves competitive results on small-scale graphs. We provide an empirical analysis of the Dirichlet energy, and show that generative models might struggle to accurately reconstruct it.