Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Yunhui, Cheng, Jiashun, Lin, Yiqing, Xie, Qizhuo, Li, Jia, Tsung, Fugee, Yin, Hongzhi, Zheng, Tao, Zhao, Jianhua, He, Tieke
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912856312643584
author Liu, Yunhui
Cheng, Jiashun
Lin, Yiqing
Xie, Qizhuo
Li, Jia
Tsung, Fugee
Yin, Hongzhi
Zheng, Tao
Zhao, Jianhua
He, Tieke
author_facet Liu, Yunhui
Cheng, Jiashun
Lin, Yiqing
Xie, Qizhuo
Li, Jia
Tsung, Fugee
Yin, Hongzhi
Zheng, Tao
Zhao, Jianhua
He, Tieke
contents Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors: (1) label scarcity stemming from the high cost of annotations and (2) homophily disparity at node and class levels. In this paper, we introduce Anomaly-Aware Pre-Training and Fine-Tuning (APF), a targeted and effective framework to mitigate the above challenges in GAD. In the pre-training stage, APF incorporates node-specific subgraphs selected via the Rayleigh Quotient, a label-free anomaly metric, into the learning objective to enhance anomaly awareness. It further introduces two learnable spectral polynomial filters to jointly learn dual representations that capture both general semantics and subtle anomaly cues. During fine-tuning, a gated fusion mechanism adaptively integrates pre-trained representations across nodes and dimensions, while an anomaly-aware regularization loss encourages abnormal nodes to preserve more anomaly-relevant information. Furthermore, we theoretically show that APF tends to achieve linear separability under mild conditions. Comprehensive experiments on 10 benchmark datasets validate the superior performance of APF in comparison to state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14250
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection
Liu, Yunhui
Cheng, Jiashun
Lin, Yiqing
Xie, Qizhuo
Li, Jia
Tsung, Fugee
Yin, Hongzhi
Zheng, Tao
Zhao, Jianhua
He, Tieke
Machine Learning
Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors: (1) label scarcity stemming from the high cost of annotations and (2) homophily disparity at node and class levels. In this paper, we introduce Anomaly-Aware Pre-Training and Fine-Tuning (APF), a targeted and effective framework to mitigate the above challenges in GAD. In the pre-training stage, APF incorporates node-specific subgraphs selected via the Rayleigh Quotient, a label-free anomaly metric, into the learning objective to enhance anomaly awareness. It further introduces two learnable spectral polynomial filters to jointly learn dual representations that capture both general semantics and subtle anomaly cues. During fine-tuning, a gated fusion mechanism adaptively integrates pre-trained representations across nodes and dimensions, while an anomaly-aware regularization loss encourages abnormal nodes to preserve more anomaly-relevant information. Furthermore, we theoretically show that APF tends to achieve linear separability under mild conditions. Comprehensive experiments on 10 benchmark datasets validate the superior performance of APF in comparison to state-of-the-art baselines.
title Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection
topic Machine Learning
url https://arxiv.org/abs/2504.14250