ANOMALYMAXQ:Anomaly-Structured Maximization to Query in Attributed Network

TL;DR

ANOMALYMAXQ is a novel method for efficiently querying anomaly subgraphs in attributed networks by decomposing query graphs into star structures, demonstrating robustness and speed on large real-world datasets.

Contribution

The paper introduces ANOMALYMAXQ, a new approach that decomposes query graphs into star structures for fast and approximate anomaly detection in attributed networks, addressing label noise issues.

Findings

High robustness in anomaly detection

Fast response time on large datasets

Effective in real-world attributed networks

Abstract

The detection of anomaly subgraphs naturally appears in various real-life tasks, yet label noise seriously interferes with the result. As a motivation for our work, we focus on inaccurate supervision and use prior knowledge to reduce effects of noise, like query graphs. Anomalies in attributed networks exhibit structured-properties, e.g., anomaly in money laundering with "ring structure" property. It is the main challenge to fast and approximate query anomaly in attributed networks. We propose a novel search method: 1) decomposing a query graph into stars; 2) sorting attributed vertices; and 3) assembling anomaly stars under the root vertex sequence into near query. We present ANOMALYMAXQ and perform on 68,411 company network (Tianyancha dataset),7.72m patent networks (Company patents) and so on. Extensive experiments show that our method has high robustness and fast response time. When running the patent dataset,the average running time to query the graph once is about 252 seconds.