.png){kind=icon}
.png){kind=icon}
Return
Attribute graph anomaly detection utilizing memory networks enhanced by multi-embedding comparison
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.129762.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In complex attribute networks, accurately pinpointing anomalous nodes is vital for grasping network behavior and safeguarding network security. Traditional anomaly detection methods often struggle to fully harness the intricate relationships that underpin attributes and structures, thus curbing their practical effectiveness. To transcend this limitation, we introduce a novel graph anomaly detection model that harmoniously integrates node attributes and structural information. Our model employs multi-embedding contrast modules, coupled with memory network enhancements, to pinpoint anomalous nodes. Precisely, we crafted a multi-embedding contrast module to encode the attributes and structures inherent within nodes, generating a multitude of embedding representations. By scrutinizing the discrepancies between these representations, our model adeptly identifies nodes that deviate from attribute and structural consistency, indicating anomalies. Furthermore, we incorporate a memory network to reconstruct node attributes, thereby enhancing the attribute decoding process while preserving the straightforwardness of structural decoding. To validate our method, we conducted extensive experiments on five authoritative public graph datasets, comparing various graph anomaly detection methods using rigorous metrics such as AUC, precision, and recall. The experimental results unequivocally demonstrate that our proposed method surpasses current state-of-the-art techniques in detecting anomalous nodes within graphs, solidly validating its efficacy.
Keywords:
Anomaly detection
Attributed networks
Deep autoencoder
Social networks