{"id":"https://openalex.org/W7166558736","doi":"https://doi.org/10.48550/arxiv.2606.28134","title":"Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection","display_name":"Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166558736","doi":"https://doi.org/10.48550/arxiv.2606.28134"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.28134","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28134","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.28134","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139597709","display_name":"Liming Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Liming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139584658","display_name":"Chao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110128334","display_name":"M A \u00c7ipilo lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Mingfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111089096","display_name":"Yiwei Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Yiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028631080","display_name":"Xin Li","orcid":"https://orcid.org/0009-0008-7072-9696"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xingle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079764771","display_name":"Heyuan Shi","orcid":"https://orcid.org/0000-0002-9040-7247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Heyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.963100016117096,"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":0.963100016117096,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.011699999682605267,"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":0.0017999999690800905,"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/graph","display_name":"Graph","score":0.5651999711990356},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4519999921321869},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.41510000824928284},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3781999945640564},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3334999978542328},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.3188999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758400022983551},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5651999711990356},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35899999737739563},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.296099990606308},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.28134","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28134","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.28134","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28134","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.8074337840080261,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph-based":[0],"fraud":[1,23,98,188],"detection":[2],"is":[3,103],"essential":[4],"for":[5,74,95],"safeguarding":[6],"large-scale":[7],"transaction":[8,165],"systems,":[9],"where":[10,33,48],"undetected":[11],"anomalies":[12,55],"may":[13,52,59],"lead":[14],"to":[15,132],"substantial":[16],"financial":[17],"losses":[18],"and":[19,30,39,45,63,91,128,147,158,190,214,216],"security":[20],"risks.":[21],"Real-world":[22],"graphs":[24],"pose":[25],"two":[26],"coupled":[27],"challenges:":[28],"sparse":[29],"imbalanced":[31],"supervision,":[32],"verified":[34],"fraudulent":[35],"labels":[36],"are":[37],"scarce":[38],"heavily":[40],"skewed":[41],"toward":[42],"benign":[43],"accounts,":[44],"representation":[46,89],"dilution,":[47],"spatial":[49],"message":[50],"passing":[51],"oversmooth":[53],"camouflaged":[54],"while":[56],"spectral":[57,93,139],"filters":[58],"suppress":[60],"fraud-relevant":[61,145],"mid-":[62],"high-frequency":[64],"irregularities.":[65],"To":[66],"address":[67],"these":[68],"challenges,":[69],"we":[70],"propose":[71],"ADC-GNN,":[72],"short":[73],"Attention-guided":[75],"Diffusion-Contrastive":[76],"Graph":[77],"Neural":[78],"Network,":[79],"a":[80,106,113,125,161,172],"unified":[81],"framework":[82],"that":[83],"combines":[84],"diffusion-guided":[85],"feature":[86],"augmentation,":[87],"contrastive":[88,130],"learning,":[90],"multi-hop":[92],"attention":[94,140],"few-shot":[96],"graph":[97,116,187,194],"detection.":[99],"The":[100,138],"diffusion":[101,117,212],"component":[102],"formulated":[104],"as":[105,171],"feature-space":[107],"denoising":[108],"augmentation":[109],"mechanism":[110],"rather":[111],"than":[112],"full":[114],"topology-generative":[115],"model:":[118],"it":[119],"constructs":[120],"noise-perturbed":[121],"node-feature":[122],"views":[123],"under":[124],"cosine":[126],"schedule":[127],"uses":[129],"learning":[131],"stabilize":[133],"node":[134],"representations":[135],"across":[136],"perturbations.":[137],"module":[141],"further":[142,219],"adaptively":[143],"emphasizes":[144],"hop-level":[146],"relation-level":[148],"cues.":[149],"We":[150],"evaluate":[151],"ADC-GNN":[152,181],"primarily":[153],"on":[154,197,203],"three":[155],"public":[156,199],"benchmarks":[157],"additionally":[159],"report":[160],"proprietary":[162],"real-world":[163],"telecom":[164],"dataset":[166],"with":[167],"approximately":[168],"60,000":[169],"records":[170],"private":[173],"case":[174],"study.":[175],"Under":[176],"the":[177,198,221],"1%":[178],"training":[179,206],"setting,":[180],"achieves":[182],"consistent":[183],"improvements":[184],"over":[185],"original":[186],"baselines":[189,196],"four":[191],"protocol-consistent":[192],"recent":[193],"anomaly/fraud":[195],"benchmarks.":[200],"Additional":[201],"analyses":[202],"split":[204],"stability,":[205],"ratios,":[207],"oversampling":[208],"alternatives,":[209],"module-level":[210],"ablations,":[211],"schedules,":[213],"runtime":[215],"memory-consumption":[217],"comparisons":[218],"characterize":[220],"effective":[222],"operating":[223],"regime":[224],"of":[225],"ADC-GNN.":[226]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-30T00:00:00"}