Loading…

Improving Graph Convolutional Network with Learnable Edge Weights and Edge-Node Co-Embedding for Graph Anomaly Detection

The era of Industry 4.0 is gradually transforming our society into a data-driven one, which can help us uncover valuable information from accumulated data, thereby improving the level of social governance. The detection of anomalies, is crucial for maintaining societal trust and fairness, yet it pos...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Switzerland), 2024-04, Vol.24 (8), p.2591
Main Authors: Tan, Xiao, Yang, Jianfeng, Zhao, Zhengang, Xiao, Jinsheng, Li, Chengwang
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c469t-7797d7d891820e509a553561a4677d461c2d1e589d802b0660049c3cb5a95b0a3
container_end_page
container_issue 8
container_start_page 2591
container_title Sensors (Basel, Switzerland)
container_volume 24
creator Tan, Xiao
Yang, Jianfeng
Zhao, Zhengang
Xiao, Jinsheng
Li, Chengwang
description The era of Industry 4.0 is gradually transforming our society into a data-driven one, which can help us uncover valuable information from accumulated data, thereby improving the level of social governance. The detection of anomalies, is crucial for maintaining societal trust and fairness, yet it poses significant challenges due to the ubiquity of anomalies and the difficulty in identifying them accurately. This paper aims to enhance the performance of the current Graph Convolutional Network (GCN)-based Graph Anomaly Detection (GAD) algorithm on datasets with extremely low proportions of anomalous labels. This goal is achieved through modifying the GCN network structure and conducting feature extraction, thus fully utilizing three types of information in the graph: node label information, node feature information, and edge information. Firstly, we theoretically demonstrate the relationship between label propagation and feature convolution, indicating that the Label Propagation Algorithm (LPA) can serve as a regularization penalty term for GCN, aiding in training and enabling learnable edge weights, providing a basis for incorporating node label information into GCN networks. Secondly, we introduce a method to aggregate node and edge features, thereby incorporating edge information into GCN networks. Finally, we design different GCN trainable weights for node features and co-embedding features. This design allows different features to be projected into different spaces, greatly enhancing model expressiveness. Experimental results on the DGraph dataset demonstrate superior AUC performance compared to baseline models, highlighting the feasibility and efficacy of the proposed approach in addressing GAD tasks in the scene with extremely low proportions of anomalous data.
doi_str_mv 10.3390/s24082591
format article
fullrecord <record><control><sourceid>gale_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_6367a72fe54648fdbf2ec9994406bc93</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A793557198</galeid><doaj_id>oai_doaj_org_article_6367a72fe54648fdbf2ec9994406bc93</doaj_id><sourcerecordid>A793557198</sourcerecordid><originalsourceid>FETCH-LOGICAL-c469t-7797d7d891820e509a553561a4677d461c2d1e589d802b0660049c3cb5a95b0a3</originalsourceid><addsrcrecordid>eNpdkktvEzEQgFcIREvhwB9AK3Ephy1-P04oCqFEqsoFxNHy2rMbh9118G5S-u9xmhC1yAdb42--8VhTFG8xuqJUo48jYUgRrvGz4hwzwipFCHr-6HxWvBrHNUKEUqpeFmdUCSkIUufFn2W_SXEXhra8TnazKudx2MVuO4U42K68hekupl_lXZhW5Q3YNNi6g3LhWyh_QmhX01jawT8EqtvoIedXi74G7_fKJqajdjbE3nb35WeYwO3lr4sXje1GeHPcL4ofXxbf51-rm2_Xy_nspnJM6KmSUksvvdJYEQQcacs55QJbJqT0TGBHPAautFeI1EgIhJh21NXcal4jSy-K5cHro12bTQq9Tfcm2mAeAjG1xqYpuA6MoEJaSRrgTDDV-Loh4LTWjCFRO02z69PBtdnWPXgHw5Rs90T69GYIK9PGncEYccoEz4bLoyHF31sYJ9OH0UHX2QHidjQUMamZEJRk9P1_6Dpu8_93BwpxhgnL1NWBam3uIAxNzIVdXh764OIATcjxmdSUc4m1ygkfDgkuxXFM0Jyej5HZT5M5TVNm3z3u90T-Gx_6Fzepwt4</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3047054124</pqid></control><display><type>article</type><title>Improving Graph Convolutional Network with Learnable Edge Weights and Edge-Node Co-Embedding for Graph Anomaly Detection</title><source>Publicly Available Content Database</source><source>PubMed Central</source><creator>Tan, Xiao ; Yang, Jianfeng ; Zhao, Zhengang ; Xiao, Jinsheng ; Li, Chengwang</creator><creatorcontrib>Tan, Xiao ; Yang, Jianfeng ; Zhao, Zhengang ; Xiao, Jinsheng ; Li, Chengwang</creatorcontrib><description>The era of Industry 4.0 is gradually transforming our society into a data-driven one, which can help us uncover valuable information from accumulated data, thereby improving the level of social governance. The detection of anomalies, is crucial for maintaining societal trust and fairness, yet it poses significant challenges due to the ubiquity of anomalies and the difficulty in identifying them accurately. This paper aims to enhance the performance of the current Graph Convolutional Network (GCN)-based Graph Anomaly Detection (GAD) algorithm on datasets with extremely low proportions of anomalous labels. This goal is achieved through modifying the GCN network structure and conducting feature extraction, thus fully utilizing three types of information in the graph: node label information, node feature information, and edge information. Firstly, we theoretically demonstrate the relationship between label propagation and feature convolution, indicating that the Label Propagation Algorithm (LPA) can serve as a regularization penalty term for GCN, aiding in training and enabling learnable edge weights, providing a basis for incorporating node label information into GCN networks. Secondly, we introduce a method to aggregate node and edge features, thereby incorporating edge information into GCN networks. Finally, we design different GCN trainable weights for node features and co-embedding features. This design allows different features to be projected into different spaces, greatly enhancing model expressiveness. Experimental results on the DGraph dataset demonstrate superior AUC performance compared to baseline models, highlighting the feasibility and efficacy of the proposed approach in addressing GAD tasks in the scene with extremely low proportions of anomalous data.</description><identifier>ISSN: 1424-8220</identifier><identifier>EISSN: 1424-8220</identifier><identifier>DOI: 10.3390/s24082591</identifier><identifier>PMID: 38676208</identifier><language>eng</language><publisher>Switzerland: MDPI AG</publisher><subject>Algorithms ; Behavior ; Classification ; Datasets ; Fraud prevention ; graph anomaly detection ; graph convolutional neural networks ; Graphs ; label propagation ; Machine learning ; Methods ; Neural networks ; Propagation ; semi-supervised learning ; Social aspects</subject><ispartof>Sensors (Basel, Switzerland), 2024-04, Vol.24 (8), p.2591</ispartof><rights>COPYRIGHT 2024 MDPI AG</rights><rights>2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2024 by the authors. 2024</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c469t-7797d7d891820e509a553561a4677d461c2d1e589d802b0660049c3cb5a95b0a3</cites><orcidid>0000-0003-2002-9073 ; 0000-0002-8869-3344 ; 0000-0002-5403-1895</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/3047054124/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/3047054124?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,25753,27924,27925,37012,37013,44590,53791,53793,75126</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38676208$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Tan, Xiao</creatorcontrib><creatorcontrib>Yang, Jianfeng</creatorcontrib><creatorcontrib>Zhao, Zhengang</creatorcontrib><creatorcontrib>Xiao, Jinsheng</creatorcontrib><creatorcontrib>Li, Chengwang</creatorcontrib><title>Improving Graph Convolutional Network with Learnable Edge Weights and Edge-Node Co-Embedding for Graph Anomaly Detection</title><title>Sensors (Basel, Switzerland)</title><addtitle>Sensors (Basel)</addtitle><description>The era of Industry 4.0 is gradually transforming our society into a data-driven one, which can help us uncover valuable information from accumulated data, thereby improving the level of social governance. The detection of anomalies, is crucial for maintaining societal trust and fairness, yet it poses significant challenges due to the ubiquity of anomalies and the difficulty in identifying them accurately. This paper aims to enhance the performance of the current Graph Convolutional Network (GCN)-based Graph Anomaly Detection (GAD) algorithm on datasets with extremely low proportions of anomalous labels. This goal is achieved through modifying the GCN network structure and conducting feature extraction, thus fully utilizing three types of information in the graph: node label information, node feature information, and edge information. Firstly, we theoretically demonstrate the relationship between label propagation and feature convolution, indicating that the Label Propagation Algorithm (LPA) can serve as a regularization penalty term for GCN, aiding in training and enabling learnable edge weights, providing a basis for incorporating node label information into GCN networks. Secondly, we introduce a method to aggregate node and edge features, thereby incorporating edge information into GCN networks. Finally, we design different GCN trainable weights for node features and co-embedding features. This design allows different features to be projected into different spaces, greatly enhancing model expressiveness. Experimental results on the DGraph dataset demonstrate superior AUC performance compared to baseline models, highlighting the feasibility and efficacy of the proposed approach in addressing GAD tasks in the scene with extremely low proportions of anomalous data.</description><subject>Algorithms</subject><subject>Behavior</subject><subject>Classification</subject><subject>Datasets</subject><subject>Fraud prevention</subject><subject>graph anomaly detection</subject><subject>graph convolutional neural networks</subject><subject>Graphs</subject><subject>label propagation</subject><subject>Machine learning</subject><subject>Methods</subject><subject>Neural networks</subject><subject>Propagation</subject><subject>semi-supervised learning</subject><subject>Social aspects</subject><issn>1424-8220</issn><issn>1424-8220</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNpdkktvEzEQgFcIREvhwB9AK3Ephy1-P04oCqFEqsoFxNHy2rMbh9118G5S-u9xmhC1yAdb42--8VhTFG8xuqJUo48jYUgRrvGz4hwzwipFCHr-6HxWvBrHNUKEUqpeFmdUCSkIUufFn2W_SXEXhra8TnazKudx2MVuO4U42K68hekupl_lXZhW5Q3YNNi6g3LhWyh_QmhX01jawT8EqtvoIedXi74G7_fKJqajdjbE3nb35WeYwO3lr4sXje1GeHPcL4ofXxbf51-rm2_Xy_nspnJM6KmSUksvvdJYEQQcacs55QJbJqT0TGBHPAautFeI1EgIhJh21NXcal4jSy-K5cHro12bTQq9Tfcm2mAeAjG1xqYpuA6MoEJaSRrgTDDV-Loh4LTWjCFRO02z69PBtdnWPXgHw5Rs90T69GYIK9PGncEYccoEz4bLoyHF31sYJ9OH0UHX2QHidjQUMamZEJRk9P1_6Dpu8_93BwpxhgnL1NWBam3uIAxNzIVdXh764OIATcjxmdSUc4m1ygkfDgkuxXFM0Jyej5HZT5M5TVNm3z3u90T-Gx_6Fzepwt4</recordid><startdate>20240418</startdate><enddate>20240418</enddate><creator>Tan, Xiao</creator><creator>Yang, Jianfeng</creator><creator>Zhao, Zhengang</creator><creator>Xiao, Jinsheng</creator><creator>Li, Chengwang</creator><general>MDPI AG</general><general>MDPI</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-2002-9073</orcidid><orcidid>https://orcid.org/0000-0002-8869-3344</orcidid><orcidid>https://orcid.org/0000-0002-5403-1895</orcidid></search><sort><creationdate>20240418</creationdate><title>Improving Graph Convolutional Network with Learnable Edge Weights and Edge-Node Co-Embedding for Graph Anomaly Detection</title><author>Tan, Xiao ; Yang, Jianfeng ; Zhao, Zhengang ; Xiao, Jinsheng ; Li, Chengwang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c469t-7797d7d891820e509a553561a4677d461c2d1e589d802b0660049c3cb5a95b0a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Behavior</topic><topic>Classification</topic><topic>Datasets</topic><topic>Fraud prevention</topic><topic>graph anomaly detection</topic><topic>graph convolutional neural networks</topic><topic>Graphs</topic><topic>label propagation</topic><topic>Machine learning</topic><topic>Methods</topic><topic>Neural networks</topic><topic>Propagation</topic><topic>semi-supervised learning</topic><topic>Social aspects</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tan, Xiao</creatorcontrib><creatorcontrib>Yang, Jianfeng</creatorcontrib><creatorcontrib>Zhao, Zhengang</creatorcontrib><creatorcontrib>Xiao, Jinsheng</creatorcontrib><creatorcontrib>Li, Chengwang</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health &amp; Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Databases</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>Health &amp; Medical Collection (Alumni Edition)</collection><collection>PML(ProQuest Medical Library)</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>Directory of Open Access Journals</collection><jtitle>Sensors (Basel, Switzerland)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tan, Xiao</au><au>Yang, Jianfeng</au><au>Zhao, Zhengang</au><au>Xiao, Jinsheng</au><au>Li, Chengwang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improving Graph Convolutional Network with Learnable Edge Weights and Edge-Node Co-Embedding for Graph Anomaly Detection</atitle><jtitle>Sensors (Basel, Switzerland)</jtitle><addtitle>Sensors (Basel)</addtitle><date>2024-04-18</date><risdate>2024</risdate><volume>24</volume><issue>8</issue><spage>2591</spage><pages>2591-</pages><issn>1424-8220</issn><eissn>1424-8220</eissn><abstract>The era of Industry 4.0 is gradually transforming our society into a data-driven one, which can help us uncover valuable information from accumulated data, thereby improving the level of social governance. The detection of anomalies, is crucial for maintaining societal trust and fairness, yet it poses significant challenges due to the ubiquity of anomalies and the difficulty in identifying them accurately. This paper aims to enhance the performance of the current Graph Convolutional Network (GCN)-based Graph Anomaly Detection (GAD) algorithm on datasets with extremely low proportions of anomalous labels. This goal is achieved through modifying the GCN network structure and conducting feature extraction, thus fully utilizing three types of information in the graph: node label information, node feature information, and edge information. Firstly, we theoretically demonstrate the relationship between label propagation and feature convolution, indicating that the Label Propagation Algorithm (LPA) can serve as a regularization penalty term for GCN, aiding in training and enabling learnable edge weights, providing a basis for incorporating node label information into GCN networks. Secondly, we introduce a method to aggregate node and edge features, thereby incorporating edge information into GCN networks. Finally, we design different GCN trainable weights for node features and co-embedding features. This design allows different features to be projected into different spaces, greatly enhancing model expressiveness. Experimental results on the DGraph dataset demonstrate superior AUC performance compared to baseline models, highlighting the feasibility and efficacy of the proposed approach in addressing GAD tasks in the scene with extremely low proportions of anomalous data.</abstract><cop>Switzerland</cop><pub>MDPI AG</pub><pmid>38676208</pmid><doi>10.3390/s24082591</doi><orcidid>https://orcid.org/0000-0003-2002-9073</orcidid><orcidid>https://orcid.org/0000-0002-8869-3344</orcidid><orcidid>https://orcid.org/0000-0002-5403-1895</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1424-8220
ispartof Sensors (Basel, Switzerland), 2024-04, Vol.24 (8), p.2591
issn 1424-8220
1424-8220
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_6367a72fe54648fdbf2ec9994406bc93
source Publicly Available Content Database; PubMed Central
subjects Algorithms
Behavior
Classification
Datasets
Fraud prevention
graph anomaly detection
graph convolutional neural networks
Graphs
label propagation
Machine learning
Methods
Neural networks
Propagation
semi-supervised learning
Social aspects
title Improving Graph Convolutional Network with Learnable Edge Weights and Edge-Node Co-Embedding for Graph Anomaly Detection
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T07%3A42%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Improving%20Graph%20Convolutional%20Network%20with%20Learnable%20Edge%20Weights%20and%20Edge-Node%20Co-Embedding%20for%20Graph%20Anomaly%20Detection&rft.jtitle=Sensors%20(Basel,%20Switzerland)&rft.au=Tan,%20Xiao&rft.date=2024-04-18&rft.volume=24&rft.issue=8&rft.spage=2591&rft.pages=2591-&rft.issn=1424-8220&rft.eissn=1424-8220&rft_id=info:doi/10.3390/s24082591&rft_dat=%3Cgale_doaj_%3EA793557198%3C/gale_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c469t-7797d7d891820e509a553561a4677d461c2d1e589d802b0660049c3cb5a95b0a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3047054124&rft_id=info:pmid/38676208&rft_galeid=A793557198&rfr_iscdi=true