Anomaly Detection in Networks via Score-Based Generative Models

TL;DR

This paper introduces a novel approach for node outlier detection in attributed graphs using score-based generative models, demonstrating competitive performance on small datasets and analyzing the challenges in energy reconstruction.

Contribution

The paper adapts score-based generative models for node outlier detection in attributed graphs, providing empirical insights into their effectiveness and limitations.

Findings

Achieves competitive results on small-scale graphs

Highlights difficulties in reconstructing Dirichlet energy with generative models

Provides empirical analysis of energy-based challenges in graph modeling

Abstract

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.