SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dong, Xiangyu, Zhang, Xingyi, Sun, Yanni, Chen, Lei, Yuan, Mingxuan, Wang, Sibo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916442390134784
author Dong, Xiangyu
Zhang, Xingyi
Sun, Yanni
Chen, Lei
Yuan, Mingxuan
Wang, Sibo
author_facet Dong, Xiangyu
Zhang, Xingyi
Sun, Yanni
Chen, Lei
Yuan, Mingxuan
Wang, Sibo
contents The smoothing issue in graph learning leads to indistinguishable node representations, posing significant challenges for graph-related tasks. However, our experiments reveal that this problem can uncover underlying properties of node anomaly detection (NAD) that previous research has missed. We introduce Individual Smoothing Patterns (ISP) and Neighborhood Smoothing Patterns (NSP), which indicate that the representations of anomalous nodes are harder to smooth than those of normal ones. In addition, we explore the theoretical implications of these patterns, demonstrating the potential benefits of ISP and NSP for NAD tasks. Motivated by these findings, we propose SmoothGNN, a novel unsupervised NAD framework. First, we design a learning component to explicitly capture ISP for detecting node anomalies. Second, we design a spectral graph neural network to implicitly learn ISP to enhance detection. Third, we design an effective coefficient based on our findings that NSP can serve as coefficients for node representations, aiding in the identification of anomalous nodes. Furthermore, we devise a novel anomaly measure to calculate loss functions and anomalous scores for nodes, reflecting the properties of NAD using ISP and NSP. Extensive experiments on 9 real datasets show that SmoothGNN outperforms the best rival by an average of 14.66% in AUC and 7.28% in Average Precision, with 75x running time speedup, validating the effectiveness and efficiency of our framework.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17525
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detection
Dong, Xiangyu
Zhang, Xingyi
Sun, Yanni
Chen, Lei
Yuan, Mingxuan
Wang, Sibo
Machine Learning
The smoothing issue in graph learning leads to indistinguishable node representations, posing significant challenges for graph-related tasks. However, our experiments reveal that this problem can uncover underlying properties of node anomaly detection (NAD) that previous research has missed. We introduce Individual Smoothing Patterns (ISP) and Neighborhood Smoothing Patterns (NSP), which indicate that the representations of anomalous nodes are harder to smooth than those of normal ones. In addition, we explore the theoretical implications of these patterns, demonstrating the potential benefits of ISP and NSP for NAD tasks. Motivated by these findings, we propose SmoothGNN, a novel unsupervised NAD framework. First, we design a learning component to explicitly capture ISP for detecting node anomalies. Second, we design a spectral graph neural network to implicitly learn ISP to enhance detection. Third, we design an effective coefficient based on our findings that NSP can serve as coefficients for node representations, aiding in the identification of anomalous nodes. Furthermore, we devise a novel anomaly measure to calculate loss functions and anomalous scores for nodes, reflecting the properties of NAD using ISP and NSP. Extensive experiments on 9 real datasets show that SmoothGNN outperforms the best rival by an average of 14.66% in AUC and 7.28% in Average Precision, with 75x running time speedup, validating the effectiveness and efficiency of our framework.
title SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detection
topic Machine Learning
url https://arxiv.org/abs/2405.17525