FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916907534254080 |
|---|---|
| author | Zhao, Yunfeng Liu, Yixin Li, Shiyuan Chen, Qingfeng Zheng, Yu Pan, Shirui |
| author_facet | Zhao, Yunfeng Liu, Yixin Li, Shiyuan Chen, Qingfeng Zheng, Yu Pan, Shirui |
| contents | Graph Anomaly Detection (GAD) aims to identify nodes that deviate from the majority within a graph, playing a crucial role in applications such as social networks and e-commerce. Despite the current advancements in deep learning-based GAD, existing approaches often suffer from high deployment costs and poor scalability due to their complex and resource-intensive training processes. Surprisingly, our empirical findings suggest that the training phase of deep GAD methods, commonly perceived as crucial, may actually contribute less to anomaly detection performance than expected. Inspired by this, we propose FreeGAD, a novel training-free yet effective GAD method. Specifically, it leverages an affinity-gated residual encoder to generate anomaly-aware representations. Meanwhile, FreeGAD identifies anchor nodes as pseudo-normal and anomalous guides, followed by calculating anomaly scores through anchor-guided statistical deviations. Extensive experiments demonstrate that FreeGAD achieves superior anomaly detection performance, efficiency, and scalability on multiple benchmark datasets from diverse domains, without any training or iterative optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10594 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection Zhao, Yunfeng Liu, Yixin Li, Shiyuan Chen, Qingfeng Zheng, Yu Pan, Shirui Machine Learning Artificial Intelligence Graph Anomaly Detection (GAD) aims to identify nodes that deviate from the majority within a graph, playing a crucial role in applications such as social networks and e-commerce. Despite the current advancements in deep learning-based GAD, existing approaches often suffer from high deployment costs and poor scalability due to their complex and resource-intensive training processes. Surprisingly, our empirical findings suggest that the training phase of deep GAD methods, commonly perceived as crucial, may actually contribute less to anomaly detection performance than expected. Inspired by this, we propose FreeGAD, a novel training-free yet effective GAD method. Specifically, it leverages an affinity-gated residual encoder to generate anomaly-aware representations. Meanwhile, FreeGAD identifies anchor nodes as pseudo-normal and anomalous guides, followed by calculating anomaly scores through anchor-guided statistical deviations. Extensive experiments demonstrate that FreeGAD achieves superior anomaly detection performance, efficiency, and scalability on multiple benchmark datasets from diverse domains, without any training or iterative optimization. |
| title | FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2508.10594 |