Graph-level anomaly detection via hierarchical memory networks

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 a...

Full description

Saved in:
Bibliographic Details
Main Authors: NIU, Chaoxi, PANG, Guansong, CHEN, Ling
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
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
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9413
record_format dspace
spelling sg-smu-ink.sis_research-94132024-01-09T03:47:47Z Graph-level anomaly detection via hierarchical memory networks NIU, Chaoxi PANG, Guansong CHEN, Ling 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. 2023-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8410 info:doi/10.1007/978-3-031-43412-9_12 https://ink.library.smu.edu.sg/context/sis_research/article/9413/viewcontent/978_3_031_39847_6.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University 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
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic 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
spellingShingle 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
NIU, Chaoxi
PANG, Guansong
CHEN, Ling
Graph-level anomaly detection via hierarchical memory networks
description 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.
format text
author NIU, Chaoxi
PANG, Guansong
CHEN, Ling
author_facet NIU, Chaoxi
PANG, Guansong
CHEN, Ling
author_sort NIU, Chaoxi
title Graph-level anomaly detection via hierarchical memory networks
title_short Graph-level anomaly detection via hierarchical memory networks
title_full Graph-level anomaly detection via hierarchical memory networks
title_fullStr Graph-level anomaly detection via hierarchical memory networks
title_full_unstemmed Graph-level anomaly detection via hierarchical memory networks
title_sort graph-level anomaly detection via hierarchical memory networks
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url 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
_version_ 1787590771024592896