{"id":"https://openalex.org/W4416251359","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228770","title":"Multi-Frequency Aware Reconstruction Model For Unsupervised Graph Anomaly Detection","display_name":"Multi-Frequency Aware Reconstruction Model For Unsupervised Graph Anomaly Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251359","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228770"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109727019","display_name":"Xinyi Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Wan","raw_affiliation_strings":["East China Normal University,Software Engineering Institute,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Software Engineering Institute,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046075384","display_name":"Pengda Li","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengda Li","raw_affiliation_strings":["East China Normal University,Software Engineering Institute,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Software Engineering Institute,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110440807","display_name":"Yihong Huang","orcid":"https://orcid.org/0000-0002-2061-5649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihong Huang","raw_affiliation_strings":["Bilibili Inc,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilibili Inc,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402281","display_name":"Liping Wang","orcid":"https://orcid.org/0000-0003-3049-9917"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Wang","raw_affiliation_strings":["East China Normal University,Software Engineering Institute,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University,Software Engineering Institute,China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16563562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.907800018787384,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.907800018787384,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.02590000070631504,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.009700000286102295,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7494999766349792},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5914000272750854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5692999958992004},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41659998893737793},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.38440001010894775},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3824999928474426},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.37389999628067017}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7494999766349792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6259999871253967},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5914000272750854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5692999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4629000127315521},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42570000886917114},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C50965678","wikidata":"https://www.wikidata.org/wiki/Q2724302","display_name":"Abnormality","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2062769337","https://openalex.org/W2134008243","https://openalex.org/W2741114205","https://openalex.org/W2808544127","https://openalex.org/W2944250323","https://openalex.org/W2954152666","https://openalex.org/W2965683718","https://openalex.org/W2998336824","https://openalex.org/W3009901425","https://openalex.org/W3015799890","https://openalex.org/W3034122135","https://openalex.org/W3048072497","https://openalex.org/W3068123808","https://openalex.org/W3093649180","https://openalex.org/W3105940150","https://openalex.org/W3133518153","https://openalex.org/W3153858161","https://openalex.org/W3169637772","https://openalex.org/W3197057534","https://openalex.org/W3206604724","https://openalex.org/W3209320371","https://openalex.org/W4221095033","https://openalex.org/W4280545892","https://openalex.org/W4327656380","https://openalex.org/W4367047347","https://openalex.org/W4379927591","https://openalex.org/W4382239148","https://openalex.org/W4385270355","https://openalex.org/W4387846516"],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0,135],"graph":[1,19],"anomaly":[2,82],"detection":[3,30,34,83],"(UGAD)":[4],"is":[5,24,91],"defined":[6],"as":[7],"identifying":[8],"abnormal":[9,46,60,119,176],"nodes":[10,47,63,120],"that":[11,115],"deviate":[12],"from":[13,96],"the":[14,42,50,56,67,86,190,207],"normal":[15,62,106],"distribution":[16],"in":[17,27,35,39,55,75,80,89,118,203],"a":[18,139,169],"without":[20,99],"any":[21],"labels,":[22],"and":[23,31,61,107,156,163,179],"widely":[25],"used":[26],"financial":[28],"fraud":[29],"spam":[32],"users":[33],"social":[36],"networks.":[37],"However,":[38],"real-world":[40,187],"datasets,":[41],"low":[43],"proportion":[44],"of":[45,52,192,200],"leads":[48],"to":[49,73,92,152,174],"prevalence":[51],"heterophily":[53,97],"edges":[54,98],"graph.":[57],"This":[58],"makes":[59],"increasingly":[64],"indistinguishable":[65],"during":[66],"neighbor":[68],"information":[69,182],"aggregation,":[70],"thus":[71],"leading":[72],"feature-smoothing":[74,95],"traditional":[76],"UGAD":[77,90],"models,":[78],"resulting":[79],"suboptimal":[81],"performance.":[84],"Therefore,":[85],"key":[87],"challenge":[88],"prevent":[93],"node":[94,181],"labeled":[100],"data,":[101],"for":[102,134],"better":[103],"differentiation":[104],"between":[105],"anomalous":[108],"nodes.To":[109],"address":[110],"this":[111],"challenge,":[112],"we":[113,127,167],"observed":[114],"an":[116,198],"increase":[117,199],"correlates":[121],"with":[122,147,206],"stronger":[123],"high-frequency":[124,177],"signals.":[125],"And":[126],"propose":[128],"MFA-UGAD":[129,144],"(Multi-Frequency":[130],"Aware":[131],"reconstruction":[132,172],"model":[133],"Graph":[136],"Anomaly":[137],"Detection),":[138],"Beta":[140],"Wavelet":[141],"kernel-based":[142],"model.":[143],"employs":[145],"encoder":[146],"multi-spectral":[148],"localized":[149],"band-pass":[150],"filters":[151],"capture":[153],"multi-order":[154],"neighborhoods":[155],"multi-frequency":[157],"signals,":[158],"effectively":[159],"detecting":[160],"both":[161],"global":[162],"local":[164],"anomalies.":[165],"Additionally,":[166],"introduce":[168],"novel":[170],"spectral":[171],"loss":[173],"amplify":[175],"signals":[178],"mitigate":[180],"feature-smoothing.":[183],"Experiments":[184],"on":[185,196],"five":[186],"datasets":[188],"validate":[189],"effectiveness":[191],"our":[193],"approach,":[194],"achieving":[195],"average":[197],"over":[201],"7.932%":[202],"AUROC":[204],"compared":[205],"top":[208],"competitors.":[209]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}