paper-with-me

홈 › Papers

DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector

2024-10-09 · Jinghan Li, Yuan Gao, Jinda Lu, Junfeng Fang, Congcong Wen, Hui Lin, Xiang Wang

Graph Anomaly Detection (GAD) is crucial for identifying abnormal entities within networks, garnering significant attention across various fields. Traditional unsupervised methods, which decode encoded latent representations of unlabeled data with a reconstruction focus, often fail to capture critical discriminative content, leading to suboptimal anomaly detection. To address these challenges, we present a Diffusion-based Graph Anomaly Detector (DiffGAD). At the heart of DiffGAD is a novel latent space learning paradigm, meticulously designed to enhance its proficiency by guiding it with discriminative content. This innovative approach leverages diffusion sampling to infuse the latent space with discriminative content and introduces a content-preservation mechanism that retains valuable information across different scales, significantly improving its adeptness at identifying anomalies with limited time and space complexity. Our comprehensive evaluation of DiffGAD, conducted on six real-world and large-scale datasets with various metrics, demonstrated its exceptional performance.

📄 PDF Abstract BibTeX arXiv:2410.06549

Code (1)

fortunato-all/LJH_DiffGAD 공식 구현 pytorch

Tasks

Anomaly DetectionGraph Anomaly Detection

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection

2024-07-02 · Chunjing Xiao, Shikang Pang, Xovee Xu, Xuan Li 외

A critical aspect of Graph Neural Networks (GNNs) is to enhance the node representations by aggregating node neighborhood information. However, when detecting anomalies, the representations of abnormal nodes are prone to…

Anomaly DetectioncounterfactualData AugmentationDenoising+1

AutoGraphAD: Unsupervised network anomaly detection using Variational Graph Autoencoders

2025-11-21 · Georgios Anyfantis, Pere Barlet-Ros arxiv

Network Intrusion Detection Systems (NIDS) are essential tools for detecting network attacks and intrusions. While extensive research has explored the use of supervised Machine Learning for attack detection and character…

Unsupervised Anomaly DetectionNetwork Intrusion DetectionContrastive Learning

BAAF: Universal Transformation of One-Class Classifiers for Unsupervised Image Anomaly Detection

2026-02-13 · Declan McIntosh, Alexandra Branzan Albu arxiv

Detecting anomalies in images and video is an essential task for multiple real-world problems, including industrial inspection, computer-assisted diagnosis, and environmental monitoring. Anomaly detection is typically fo…

Unsupervised Anomaly Detection

Synthetic Image Detection via Spectral Gaps of QC-RBIM Nishimori Bethe-Hessian Operators

2025-08-27 · V. S. Usatyuk, D. A. Sapozhnikov, S. I. Egorov arxiv

The rapid advance of deep generative models such as GANs and diffusion networks now produces images that are virtually indistinguishable from genuine photographs, undermining media forensics and biometric security. Super…

Multi-class Anomaly Detection

Unsupervised Anomaly Detection in Stream Data with Online Evolving Spiking Neural Networks

2019-12-18 · Piotr S. Maciąg, Marzena Kryszkiewicz, Robert Bembenik, Jesus L. Lobo 외

Unsupervised anomaly discovery in stream data is a research topic with many practical applications. However, in many cases, it is not easy to collect enough training data with labeled anomalies for supervised learning of…

Anomaly DetectionTime Series AnalysisUnsupervised Anomaly Detection