RQPool: A Novel Multi-Branch Graph-Level Anomaly Detection

Anomaly Detection (AD) is crucial across various domains,as it identifies irregularities or unusual patternsthat, if quickly addressed, can prevent financial and datalosses, protect health, and prevent disasters. Many systemssuch as social networks, communication systems,and biological networks are naturally represented asgraphs with entities as nodes and interactions as edges.By analyzing these structures, we can uncover anomaliesthat are not apparent using traditional methods.However, current Graph-based AD techniques face significantchallenges, particularly low accuracy on largerdatasets. As datasets grow larger, the complexity ofthe graphs increases. This complexity makes it morechallenging for models to distinguish normal variationsfrom true anomalies. Moreover, existing Graph NeuralNetwork (GNN) algorithms focus primarily on spatialdomain features while neglecting spectral properties.Furthermore, most algorithms concentrate on intra-graphproperties such as edges and nodes, while overlookingrich global inter-graph relationships like GraphSimilarity Measures and Cross-Graph Connectivity. Toaddress these challenges, we propose a novel hybridmethod, RQPool, which integrates intra-graph spectralproperties and inter-graph spatial properties intoa unified Graph-level Anomaly Detection classifier. Inempirical evaluations across multiple datasets, RQPoolconsistently achieves higher AUC and macro-F1 scores compared topurely spectral or spatial baselines, the current state-of-the-art approaches, particularly excelling on large-scalegraphs.