paper-with-me

홈 › Papers

Flex-GAD : Flexible Graph Anomaly Detection

2025-10-29 · Apu Chakraborty, Anshul Kumar, Gagan Raj Gupta arxiv

Detecting anomalous nodes in attributed networks, where each node is associated with both structural connections and descriptive attributes, is essential for identifying fraud, misinformation, and suspicious behavior in domains such as social networks, academic citation graphs, and e-commerce platforms. We propose Flex-GAD, a novel unsupervised framework for graph anomaly detection at the node level. Flex-GAD integrates two encoders to capture complementary aspects of graph data. The framework incorporates a novel community-based GCN encoder to model intra-community and inter-community information into node embeddings, thereby ensuring structural consistency, along with a standard attribute encoder. These diverse representations are fused using a self-attention-based representation fusion module, which enables adaptive weighting and effective integration of the encoded information. This fusion mechanism allows automatic emphasis of the most relevant node representation across different encoders. We evaluate Flex-GAD on seven real-world attributed graphs with varying sizes, node degrees, and attribute homogeneity. Flex-GAD achieves an average AUC improvement of 7.98% over the previously best-performing method, GAD-NR, demonstrating its effectiveness and flexibility across diverse graph structures. Moreover, it significantly reduces training time, running 102x faster per epoch than Anomaly DAE and 3x faster per epoch than GAD-NR on average across seven benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2510.25809

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Anomaly Detection

Similar Papers 제목 키워드 기반

AddGraph_ Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN

2019-06-24 · (IJCAI 2019 6 · Li Zheng, Zhenpeng Li, Jian Li, Zhao Li, and Jun Gao

Anomaly detection in dynamic graphs becomes very critical in many different application scenarios, e.g., recommender systems, while it also raises huge challenges due to the high flexible nature of anomaly and lack o…

Anomaly DetectionEdge DetectionRecommendation Systems

GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Maps

2023-11-10 · Yifei Yang, Peng Wang, Xiaofan He, Dongmian Zou

Detecting unusual patterns in graph data is a crucial task in data mining. However, existing methods face challenges in consistently achieving satisfactory performance and often lack interpretability, which hinders our u…

Anomaly DetectionDecision MakingGraph Anomaly DetectionGraph Classification

Group Anomaly Detection using Flexible Genre Models

2011-12-01 · NeurIPS 2011 12 · Liang Xiong, Barnabás Póczos, Jeff G. Schneider

An important task in exploring and analyzing real-world data sets is to detect unusual and interesting phenomena. In this paper, we study the group anomaly detection problem. Unlike traditional anomaly detection research…

Anomaly DetectionGroup Anomaly Detection

A Flexible Framework for Anomaly Detection via Dimensionality Reduction

2019-09-09 · Alireza Vafaei Sadr, Bruce A. Bassett, Martin Kunz

Anomaly detection is challenging, especially for large datasets in high dimensions. Here we explore a general anomaly detection framework based on dimensionality reduction and unsupervised clustering. We release DRAMA, a…

Active LearningAnomaly DetectionClusteringDimensionality Reduction

Online Detection of Anomalies in Temporal Knowledge Graphs with Interpretability

2024-08-01 · Jiasheng Zhang, Rex Ying, Jie Shao

Temporal knowledge graphs (TKGs) are valuable resources for capturing evolving relationships among entities, yet they are often plagued by noise, necessitating robust anomaly detection mechanisms. Existing dynamic graph …

Anomaly DetectionGraph Anomaly DetectionKnowledge Graphs