Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916581677727744 |
|---|---|
| author | Hao, Yitong He, Enbo Zhang, Yue Yin, Guisheng |
| author_facet | Hao, Yitong He, Enbo Zhang, Yue Yin, Guisheng |
| contents | Graph anomaly detection (GAD) aims to identify nodes from a graph that are significantly different from normal patterns. Most previous studies are model-driven, focusing on enhancing the detection effect by improving the model structure. However, these approaches often treat all nodes equally, neglecting the different contributions of various nodes to the training. Therefore, we introduce graph curriculum learning as a simple and effective plug-and-play module to optimize GAD methods. The existing graph curriculum learning mainly focuses on the homogeneity of graphs and treats nodes with high homogeneity as easy nodes. In fact, GAD models can handle not only graph homogeneity but also heterogeneity, which leads to the unsuitability of these existing methods. To address this problem, we propose an innovative Bi-directional Curriculum Learning strategy (BCL), which considers nodes with higher and lower similarity to neighbor nodes as simple nodes in the direction of focusing on homogeneity and focusing on heterogeneity, respectively, and prioritizes their training. Extensive experiments show that BCL can be quickly integrated into existing detection processes and significantly improves the performance of ten GAD anomaly detection models on seven commonly used datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14197 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity Hao, Yitong He, Enbo Zhang, Yue Yin, Guisheng Machine Learning Social and Information Networks Graph anomaly detection (GAD) aims to identify nodes from a graph that are significantly different from normal patterns. Most previous studies are model-driven, focusing on enhancing the detection effect by improving the model structure. However, these approaches often treat all nodes equally, neglecting the different contributions of various nodes to the training. Therefore, we introduce graph curriculum learning as a simple and effective plug-and-play module to optimize GAD methods. The existing graph curriculum learning mainly focuses on the homogeneity of graphs and treats nodes with high homogeneity as easy nodes. In fact, GAD models can handle not only graph homogeneity but also heterogeneity, which leads to the unsuitability of these existing methods. To address this problem, we propose an innovative Bi-directional Curriculum Learning strategy (BCL), which considers nodes with higher and lower similarity to neighbor nodes as simple nodes in the direction of focusing on homogeneity and focusing on heterogeneity, respectively, and prioritizes their training. Extensive experiments show that BCL can be quickly integrated into existing detection processes and significantly improves the performance of ten GAD anomaly detection models on seven commonly used datasets. |
| title | Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2501.14197 |