Data Augmentation for Supervised Graph Outlier Detection via Latent Diffusion Models
This addresses the problem of limited outlier data for researchers and practitioners in graph analysis, though it is incremental as it applies existing diffusion models to a new domain.
The paper tackles class imbalance in supervised graph outlier detection by introducing GODM, a data augmentation method using latent diffusion models, which improves performance across multiple datasets.
A fundamental challenge confronting supervised graph outlier detection algorithms is the prevalent problem of class imbalance, where the scarcity of outlier instances compared to normal instances often results in suboptimal performance. Recently, generative models, especially diffusion models, have demonstrated their efficacy in synthesizing high-fidelity images. Despite their extraordinary generation quality, their potential in data augmentation for supervised graph outlier detection remains largely underexplored. To bridge this gap, we introduce GODM, a novel data augmentation for mitigating class imbalance in supervised Graph Outlier detection via latent Diffusion Models. Extensive experiments conducted on multiple datasets substantiate the effectiveness and efficiency of GODM. The case study further demonstrated the generation quality of our synthetic data. To foster accessibility and reproducibility, we encapsulate GODM into a plug-and-play package and release it at PyPI: https://pypi.org/project/godm/.