Graph-level anomaly detection via hierarchical memory networks

• Main Authors: NIU, Chaoxi, PANG, Guansong, CHEN, Ling
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Anomaly detection; Auto enc; oders; Fine grained; Graph neural networks; Graph-level anomaly detection; Hierarchical memory; Learn+; Memory modules; Memory network; Node attribute; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8410; https://ink.library.smu.edu.sg/context/sis_research/article/9413/viewcontent/978_3_031_39847_6.pdf
• Institution: Singapore Management University

Graph-level anomaly detection aims to identify abnormal graphs that exhibit deviant structures and node attributes compared to the majority in a graph set. One primary challenge is to learn normal patterns manifested in both fine-grained and holistic views of graphs for identifying graphs that are abnormal in part or in whole. To tackle this challenge, we propose a novel approach called Hierarchical Memory Networks (HimNet), which learns hierarchical memory modules---node and graph memory modules---via a graph autoencoder network architecture. The node-level memory module is trained to model fine-grained, internal graph interactions among nodes for detecting locally abnormal graphs, while the graph-level memory module is dedicated to the learning of holistic normal patterns for detecting globally abnormal graphs. The two modules are jointly optimized to detect both locally- and globally-anomalous graphs. Extensive empirical results on 16 real-world graph datasets from various domains show that i) HimNet significantly outperforms the state-of-art methods and ii) it is robust to anomaly contamination. Codes are available at: https://github.com/Niuchx/HimNet.