{"id":"https://openalex.org/W7152400112","doi":"https://doi.org/10.1145/3774904.3792307","title":"Revisiting Graph-Level Anomaly Detection: From Partially to Fully Unsupervised Learning","display_name":"Revisiting Graph-Level Anomaly Detection: From Partially to Fully Unsupervised Learning","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152400112","doi":"https://doi.org/10.1145/3774904.3792307"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792307","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792307","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792307","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100433327","display_name":"Zhenyu Yang","orcid":"https://orcid.org/0000-0002-6588-3014"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhenyu Yang","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6588-3014","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066698067","display_name":"Ge Zhang","orcid":"https://orcid.org/0000-0001-6009-780X"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Zhang","raw_affiliation_strings":["School of Information and Intelligent Science, Donghua University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6009-780X","affiliations":[{"raw_affiliation_string":"School of Information and Intelligent Science, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912402","display_name":"Shan Xue","orcid":"https://orcid.org/0000-0002-9123-5133"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shan Xue","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9123-5133","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085139646","display_name":"Xiaoxiao Ma","orcid":"https://orcid.org/0000-0003-1270-4155"},"institutions":[{"id":"https://openalex.org/I2802690124","display_name":"Sydney Water","ror":"https://ror.org/04yhf7405","country_code":"AU","type":"government","lineage":["https://openalex.org/I2801351115","https://openalex.org/I2802690124"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaoxiao Ma","raw_affiliation_strings":["Oracle Corporation, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1270-4155","affiliations":[{"raw_affiliation_string":"Oracle Corporation, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I2802690124"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Yang","orcid":"https://orcid.org/0000-0002-4408-1952"},"institutions":[{"id":"https://openalex.org/I12615008","display_name":"Beijing Normal-Hong Kong Baptist University","ror":"https://ror.org/04snvc712","country_code":"CN","type":"education","lineage":["https://openalex.org/I12615008"]},{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Faculty of Science and Technology, Beijing Normal-Hong Kong Baptist University, Zhuhai, Guangdong, Australia and School of Computing, Macquarie University, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4408-1952","affiliations":[{"raw_affiliation_string":"Faculty of Science and Technology, Beijing Normal-Hong Kong Baptist University, Zhuhai, Guangdong, Australia and School of Computing, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I12615008","https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Peng","orcid":"https://orcid.org/0000-0003-0458-5977"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Peng","raw_affiliation_strings":["School of Cyber Science and Technology, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0458-5977","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056293251","display_name":"Amin Beheshti","orcid":"https://orcid.org/0000-0002-5988-5494"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Amin Beheshti","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5988-5494","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133284606","display_name":"Jia Wu","orcid":"https://orcid.org/0000-0002-1371-5801"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jia Wu","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1371-5801","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"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":0.51580662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"901","last_page":"912"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.39989998936653137,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.39989998936653137,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.186599999666214,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.060499999672174454,"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/unsupervised-learning","display_name":"Unsupervised learning","score":0.5613999962806702},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.48240000009536743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3666999936103821},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3614000082015991},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.32429999113082886},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3037000000476837}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5809999704360962},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5130000114440918},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792307","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792307","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792307","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792307","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1560021816","https://openalex.org/W1978904760","https://openalex.org/W1985690171","https://openalex.org/W2056562706","https://openalex.org/W2089554624","https://openalex.org/W2964030506","https://openalex.org/W3089028909","https://openalex.org/W3102100346","https://openalex.org/W3114932221","https://openalex.org/W3153567752","https://openalex.org/W4376121550","https://openalex.org/W4393140156","https://openalex.org/W4402530312","https://openalex.org/W4409365127","https://openalex.org/W4412196746","https://openalex.org/W7085013484","https://openalex.org/W7117317549"],"related_works":[],"abstract_inverted_index":{"Graph-level":[0],"anomaly":[1,164],"detection":[2,165],"(GLAD)":[3],"is":[4,65,157],"a":[5,55,71,82,89,177],"critical":[6],"task":[7],"to":[8,22,60,115,184],"identify":[9],"graphs":[10,200],"with":[11,96],"abnormal":[12],"properties":[13],"in":[14],"various":[15],"domains,":[16],"ranging":[17],"from":[18,201],"fraudulent":[19],"social":[20,202],"networks":[21,203],"malicious":[23],"botnets":[24],"on":[25,40,92,194],"online":[26,205],"platforms.":[27],"The":[28],"dominant":[29],"paradigm":[30,52],"for":[31],"existing":[32,136],"GLAD":[33,114,137],"detectors":[34,138],"has":[35],"been":[36],"partially":[37,50],"unsupervised,":[38],"relying":[39],"training":[41,63,88],"data":[42,64,94],"composed":[43],"exclusively":[44],"of":[45,67,81,100,153,190,210,217],"normal":[46,101],"samples.":[47,104],"However,":[48],"this":[49,107],"unsupervised":[51,84,118,222],"inevitably":[53],"requires":[54],"costly":[56],"expert":[57],"filtering":[58],"process":[59],"ensure":[61],"the":[62,78,146,151,186,208,215],"free":[66],"anomalies.":[68,155],"This":[69],"creates":[70],"significant":[72],"gap":[73],"between":[74],"current":[75],"approaches":[76],"and":[77,102,128,166,188,204,213],"real-world":[79,93,199],"necessity":[80],"fully":[83,117,221],"paradigm,":[85],"which":[86],"involves":[87],"model":[90],"directly":[91],"''as-is'',":[95],"its":[97],"inherent":[98],"mix":[99],"anomalous":[103],"To":[105],"bridge":[106],"gap,":[108],"we":[109,175],"incorporate":[110],"uncertainty":[111,141,167,219],"learning":[112],"into":[113,220],"promote":[116],"learning.":[119],"We":[120],"propose":[121],"two":[122],"frameworks:":[123],"Score":[124],"Uncertainty":[125,130],"Learning":[126,131],"(SUL)":[127],"Graph-data":[129],"(GUL).":[132],"Specifically,":[133],"SUL":[134],"enhances":[135],"by":[139],"modeling":[140,168],"through":[142],"Gaussian":[143],"distributions":[144],"over":[145],"detectors'":[147],"predictions,":[148],"adaptively":[149],"attenuating":[150],"influence":[152],"potential":[154,182],"GUL":[156],"an":[158,170],"end-to-end":[159],"framework":[160],"that":[161,180],"iteratively":[162],"optimizes":[163],"via":[169],"Expectation-Maximization":[171],"algorithm.":[172],"In":[173],"addition,":[174],"develop":[176],"dedicated":[178],"loss":[179],"utilizes":[181],"anomalies":[183],"enhance":[185],"effectiveness":[187],"robustness":[189],"GUL.":[191],"Empirical":[192],"results":[193],"sixteen":[195],"benchmark":[196],"datasets,":[197],"covering":[198],"platforms,":[206],"demonstrate":[207],"superiority":[209],"our":[211],"methods":[212],"highlight":[214],"promise":[216],"incorporating":[218],"GLAD.":[223]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}