arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.04086cs.LGcs.AI
收藏

DeNoise:学习鲁棒图表示用于无监督图级异常检测

DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detection

School of Computer, Electronics and Information, Guangxi University(广西大学计算机电子信息学院);School of Computer Science and Technology, Hainan University(海南大学计算机科学与技术学院);Guangxi Key Laboratory of Multi-Source Information Mining & Security, Guangxi Normal University(广西多源信息挖掘与安全重点实验室)

Qingfeng Chen, Haojin Zeng, Jingyi Jie, Shichao Zhang, Debo Cheng

AI总结:

针对无监督图级异常检测中训练数据易受异常图污染的问题,提出DeNoise框架,通过对抗学习、锚点对齐去噪和对比学习学习抗噪声图表示,在多个数据集上显著优于现有方法。

摘要:

随着关键领域中图结构数据的快速增长,无监督图级异常检测(UGAD)已成为一项关键任务。UGAD旨在识别整体偏离正常行为模式的图。然而,大多数图神经网络(GNN)方法隐含地假设训练集是干净的,只包含正常图,这在实际中很少成立。即使少量异常图污染也可能扭曲所学表示并显著降低性能。为应对这一挑战,我们提出DeNoise,一个专为受污染训练数据设计的鲁棒UGAD框架。它通过对抗目标联合优化图级编码器、属性解码器和结构解码器,以学习抗噪声嵌入。此外,DeNoise引入了一种编码器锚点对齐去噪机制,将来自正常图的高信息节点嵌入融合到所有图嵌入中,在抑制异常干扰的同时提升表示质量。随后,对比学习组件在潜在空间中压缩正常图嵌入并排斥异常图嵌入。在八个真实世界数据集上的大量实验表明,DeNoise在不同噪声强度下始终能学习到可靠的图级表示,并显著优于最先进的UGAD基线。

英文摘要:

With the rapid growth of graph-structured data in critical domains, unsupervised graph-level anomaly detection (UGAD) has become a pivotal task. UGAD seeks to identify entire graphs that deviate from normal behavioral patterns. However, most Graph Neural Network (GNN) approaches implicitly assume that the training set is clean, containing only normal graphs, which is rarely true in practice. Even modest contamination by anomalous graphs can distort learned representations and sharply degrade performance. To address this challenge, we propose DeNoise, a robust UGAD framework explicitly designed for contaminated training data. It jointly optimizes a graph-level encoder, an attribute decoder, and a structure decoder via an adversarial objective to learn noise-resistant embeddings. Further, DeNoise introduces an encoder anchor-alignment denoising mechanism that fuses high-information node embeddings from normal graphs into all graph embeddings, improving representation quality while suppressing anomaly interference. A contrastive learning component then compacts normal graph embeddings and repels anomalous ones in the latent space. Extensive experiments on eight real-world datasets demonstrate that DeNoise consistently learns reliable graph-level representations under varying noise intensities and significantly outperforms state-of-the-art UGAD baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑