Balanced Anomaly-guided Ego-graph Diffusion Model for Inductive Graph Anomaly Detection

2026-02-05

AI Summary

This work addresses the challenges of dynamic graph modeling and extreme class imbalance in inductive graph anomaly detection by proposing a novel data-centric framework. The approach uniquely integrates a discrete autoregressive graph diffusion model with a curriculum-based anomaly augmentation mechanism: the former generates local subgraphs that faithfully reflect the structural distribution of real anomalies, while the latter dynamically emphasizes underrepresented anomaly patterns during training, enabling adaptive and balanced data generation. By decoupling the inherent tension between model staticity and data imbalance, the framework significantly enhances the detection performance and generalization capability for unseen anomalous nodes across five benchmark datasets.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Graph anomaly detection (GAD) is crucial in applications like fraud detection and cybersecurity. Despite recent advancements using graph neural networks (GNNs), two major challenges persist. At the model level, most methods adopt a transductive learning paradigm, which assumes static graph structures, making them unsuitable for dynamic, evolving networks. At the data level, the extreme class imbalance, where anomalous nodes are rare, leads to biased models that fail to generalize to unseen anomalies. These challenges are interdependent: static transductive frameworks limit effective data augmentation, while imbalance exacerbates model distortion in inductive learning settings. To address these challenges, we propose a novel data-centric framework that integrates dynamic graph modeling with balanced anomaly synthesis. Our framework features: (1) a discrete ego-graph diffusion model, which captures the local topology of anomalies to generate ego-graphs aligned with anomalous structural distribution, and (2) a curriculum anomaly augmentation mechanism, which dynamically adjusts synthetic data generation during training, focusing on underrepresented anomaly patterns to improve detection and generalization. Experiments on five datasets demonstrate that the effectiveness of our framework.

Problem

• graph anomaly detection
• inductive learning
• class imbalance
• dynamic graphs
• anomaly generalization

Innovation

• ego-graph diffusion
• inductive graph anomaly detection
• anomaly synthesis
• class imbalance
• curriculum augmentation