{"id":"https://openalex.org/W7161977764","doi":"https://doi.org/10.48550/arxiv.2605.20879","title":"NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversity","display_name":"NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversity","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7161977764","doi":"https://doi.org/10.48550/arxiv.2605.20879"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20879","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20879","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"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.2605.20879","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136613406","display_name":"Kaifeng Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Kaifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136706978","display_name":"Teng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Teng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136613403","display_name":"Liang Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043803804","display_name":"Xiubo Liang","orcid":"https://orcid.org/0000-0002-4749-5552"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Xiubo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136684235","display_name":"Yuke Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yuke","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.6051999926567078,"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":0.6051999926567078,"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":0.2680000066757202,"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":0.025499999523162842,"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":0.6541000008583069},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6166999936103821},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5774000287055969},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5315999984741211},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4950999915599823},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.45010000467300415},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.35519999265670776},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6541000008583069},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6166999936103821},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5475000143051147},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44909998774528503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3824999928474426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3723999857902527},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2779982251","wikidata":"https://www.wikidata.org/wiki/Q25053762","display_name":"Stochastic block model","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2655999958515167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20879","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20879","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20879","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20879","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7613299489021301,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0],"Anomaly":[1],"Detection":[2],"(GAD)":[3],"is":[4,99],"increasingly":[5],"shifting":[6],"to":[7,82],"Generalist":[8],"GAD":[9],"(GGAD)":[10],"for":[11,32],"cross-domain":[12,51],"\"one-for-all\"":[13],"detection,":[14],"but":[15],"existing":[16],"GGAD":[17,140,199],"methods":[18,36],"predominantly":[19],"rely":[20],"on":[21,68],"the":[22,28,73,80,83,90,111,162],"neighbor":[23,69,97,108],"consistency":[24,133],"principle,":[25],"falling":[26],"into":[27],"\\textbf{Node-to-Neighbor":[29],"Consistency":[30,76],"Paradigm}":[31],"anomaly":[33,64,104],"quantification.":[34],"These":[35],"suffer":[37],"from":[38,72],"complex":[39],"training":[40,43],"pipelines,":[41],"heavy":[42],"data":[44],"dependency,":[45],"high":[46],"computational":[47],"costs,":[48],"and":[49,87,127,156,170,192,196],"unstable":[50],"generalization.":[52],"To":[53],"address":[54],"these":[55],"limitations,":[56],"we":[57,78],"propose":[58],"NeighborDiv,":[59],"a":[60,95,100,120,194],"training-free":[61],"generalist":[62],"graph":[63,125],"detection":[65],"framework":[66],"based":[67],"diversity.":[70],"Departing":[71],"dominant":[74],"Node-to-Neighbor":[75],"Paradigm,":[77],"shift":[79],"focus":[81],"\\textbf{Neighbor-to-Neighbor":[84],"Diversity":[85],"Paradigm},":[86],"uncover":[88],"that":[89],"internal":[91],"structural":[92],"dispersion":[93],"of":[94,113,130,151],"node's":[96],"set":[98],"powerful,":[101],"independently":[102,129],"discriminative":[103],"signal.":[105],"We":[106],"quantify":[107],"diversity":[109],"via":[110],"variance":[112],"inter-neighbor":[114],"feature":[115],"similarities,":[116],"which":[117],"captures":[118],"how":[119],"node":[121],"organizes":[122],"its":[123],"local":[124],"environment,":[126],"operates":[128],"conventional":[131],"node-to-neighbor":[132],"frameworks.":[134],"Extensive":[135],"experiments":[136],"under":[137,165,174],"two":[138],"standard":[139],"evaluation":[141],"paradigms":[142],"show":[143],"NeighborDiv":[144,181],"achieves":[145],"state-of-the-art":[146],"performance,":[147],"with":[148],"relative":[149],"gains":[150],"10.25%":[152],"in":[153,158,172],"average":[154,159],"AUC":[155],"17.78%":[157],"AP":[160],"over":[161],"second-best":[163],"baseline":[164],"Single-Domain":[166],"Independent":[167],"Training":[168,177],"(SDIT),":[169],"6.89%/9.58%":[171],"AUC/AP":[173],"Unified":[175],"Multi-Domain":[176],"(UMDT),":[178],"respectively.":[179],"Notably,":[180],"yields":[182],"zero":[183],"performance":[184],"volatility":[185],"across":[186],"all":[187],"datasets,":[188],"eliminating":[189],"training-set":[190],"dependency":[191],"establishing":[193],"lightweight":[195],"highly":[197],"practical":[198],"framework.":[200]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-22T00:00:00"}