Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.00734 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914857012428800 |
|---|---|
| author | Xu, Fan Wang, Nan Wu, Hao Wen, Xuezhi Zhang, Dalin Lu, Siyang Li, Binyong Gong, Wei Wan, Hai Zhao, Xibin |
| author_facet | Xu, Fan Wang, Nan Wu, Hao Wen, Xuezhi Zhang, Dalin Lu, Siyang Li, Binyong Gong, Wei Wan, Hai Zhao, Xibin |
| contents | Graph-Level Anomaly Detection (GLAD) aims to distinguish anomalous graphs within a graph dataset. However, current methods are constrained by their receptive fields, struggling to learn global features within the graphs. Moreover, most contemporary methods are based on spatial domain and lack exploration of spectral characteristics. In this paper, we propose a multi-perspective hybrid graph-level anomaly detector namely GLADformer, consisting of two key modules. Specifically, we first design a Graph Transformer module with global spectrum enhancement, which ensures balanced and resilient parameter distributions by fusing global features and spectral distribution characteristics. Furthermore, to uncover local anomalous attributes, we customize a band-pass spectral GNN message passing module that further enhances the model's generalization capability. Through comprehensive experiments on ten real-world datasets from multiple domains, we validate the effectiveness and robustness of GLADformer. This demonstrates that GLADformer outperforms current state-of-the-art models in graph-level anomaly detection, particularly in effectively capturing global anomaly representations and spectral characteristics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00734 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GLADformer: A Mixed Perspective for Graph-level Anomaly Detection Xu, Fan Wang, Nan Wu, Hao Wen, Xuezhi Zhang, Dalin Lu, Siyang Li, Binyong Gong, Wei Wan, Hai Zhao, Xibin Machine Learning Graph-Level Anomaly Detection (GLAD) aims to distinguish anomalous graphs within a graph dataset. However, current methods are constrained by their receptive fields, struggling to learn global features within the graphs. Moreover, most contemporary methods are based on spatial domain and lack exploration of spectral characteristics. In this paper, we propose a multi-perspective hybrid graph-level anomaly detector namely GLADformer, consisting of two key modules. Specifically, we first design a Graph Transformer module with global spectrum enhancement, which ensures balanced and resilient parameter distributions by fusing global features and spectral distribution characteristics. Furthermore, to uncover local anomalous attributes, we customize a band-pass spectral GNN message passing module that further enhances the model's generalization capability. Through comprehensive experiments on ten real-world datasets from multiple domains, we validate the effectiveness and robustness of GLADformer. This demonstrates that GLADformer outperforms current state-of-the-art models in graph-level anomaly detection, particularly in effectively capturing global anomaly representations and spectral characteristics. |
| title | GLADformer: A Mixed Perspective for Graph-level Anomaly Detection |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.00734 |