{"id":"https://openalex.org/W7204751670","doi":"https://doi.org/10.48550/arxiv.2608.27574","title":"Self-Explainable Multi-Label Graph Neural Network for Correlated Evidence Attribution","display_name":"Self-Explainable Multi-Label Graph Neural Network for Correlated Evidence Attribution","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204751670","doi":"https://doi.org/10.48550/arxiv.2608.27574"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.27574","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27574","pdf_url":"https://arxiv.org/pdf/2608.27574","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.27574","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055761987","display_name":"Yingqi Feng","orcid":"https://orcid.org/0000-0002-0269-8006","observed_orcids":["https://orcid.org/0000-0002-0269-8006"]},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng, Yingqi","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science , Florida Atlantic University , Boca Raton , FL , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science , Florida Atlantic University , Boca Raton , FL , USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148795643","display_name":"Yufei Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tang, Yufei","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science , Florida Atlantic University , Boca Raton , FL , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science , Florida Atlantic University , Boca Raton , FL , USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148783902","display_name":"Min Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi, Min","raw_affiliation_strings":["School of Computing and Informatics , University of Louisiana at Lafayette , Lafayette , LA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Informatics , University of Louisiana at Lafayette , Lafayette , LA , USA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084641325","display_name":"Xingquan Zhu A","orcid":"https://orcid.org/0000-0003-4129-9611","observed_orcids":["https://orcid.org/0000-0003-4129-9611"]},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Xingquan","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science , Florida Atlantic University , Boca Raton , FL , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science , Florida Atlantic University , Boca Raton , FL , USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.6523000001907349,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.6523000001907349,"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":0.33959999680519104,"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":0.0013000000035390258,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/edge-importance","display_name":"edge importance","score":0.3409999907016754},{"id":"https://openalex.org/keywords/label-correlation","display_name":"label correlation","score":0.718999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6308000087738037},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6248000264167786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.558899998664856},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4887999892234802},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3560999929904938},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27574","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27574","pdf_url":"https://arxiv.org/pdf/2608.27574","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27574","doi":"https://doi.org/10.48550/arxiv.2608.27574","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27574","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,"listed_in":[],"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":"pmh:oai:arXiv.org:2608.27574","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27574","pdf_url":"https://arxiv.org/pdf/2608.27574","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204751670.pdf","grobid_xml":"https://content.openalex.org/works/W7204751670.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-label":[0],"graph":[1,32,46,61,97],"learning":[2,33],"intends":[3],"to":[4,18,103,113,145],"capture":[5],"the":[6],"intrinsic":[7],"complexity":[8],"of":[9,23,30,38,159],"real-world":[10,179],"applications,":[11],"where":[12],"one":[13],"sample":[14],"is":[15],"often":[16],"related":[17],"multiple":[19,24],"groups":[20],"or":[21,69,84,194],"consists":[22],"objects.":[25],"To":[26],"date,":[27],"a":[28,73,92,127,130,135,160],"handful":[29],"multi-label":[31,60,96,147,180],"methods":[34],"exist,":[35],"but":[36],"none":[37],"them":[39],"integrate":[40],"training-time":[41],"interpretation":[42],"capability.":[43],"While":[44],"post-hoc":[45,75,122],"explainers":[47],"have":[48],"been":[49],"developed,":[50],"they":[51],"do":[52],"not":[53],"explicitly":[54],"model":[55],"label-dependent":[56],"evidence":[57,80],"sharing":[58],"in":[59,182],"learners,":[62],"especially":[63],"when":[64],"label":[65,153],"pairs":[66],"are":[67,143],"weakly":[68],"negatively":[70],"associated.":[71],"As":[72],"result,":[74],"approaches":[76],"may":[77],"miss":[78],"how":[79],"should":[81],"be":[82,163],"shared":[83],"separated":[85],"across":[86],"different":[87,157],"labels.":[88,119],"This":[89],"paper":[90],"advances":[91],"new":[93],"end-to-end":[94],"self-explainable":[95],"neural":[98],"network":[99],"(SEMGNN),":[100],"which":[101],"aims":[102],"simultaneously":[104],"classify":[105],"multi-labeled":[106],"nodes":[107],"and":[108,129,138,150,174,178,186,202],"identify":[109],"edges":[110],"significantly":[111],"contributing":[112],"each":[114],"target":[115],"node":[116,148,161],"w.r.t.":[117],"predicted":[118],"Different":[120],"from":[121],"methods,":[123],"SEMGNN":[124,191],"jointly":[125],"learns":[126],"predictor":[128],"sparse":[131],"edge-mask":[132],"explainer":[133],"within":[134],"unified":[136],"framework":[137],"training":[139],"objective.":[140],"Label-label":[141],"correlations":[142],"used":[144],"improve":[146],"classification":[149],"enhance":[151],"individual":[152],"explanations,":[154],"so":[155],"that":[156,190],"labels":[158],"can":[162],"supported":[164],"by":[165],"distinct":[166],"yet":[167],"coherent":[168],"structural":[169],"and/or":[170],"correlated":[171],"evidence.":[172],"Experiments":[173],"comparisons":[175],"on":[176],"synthetic":[177],"networks,":[181],"social":[183],"networking,":[184],"entertainment,":[185],"life":[187],"sciences,":[188],"show":[189],"achieves":[192],"competitive":[193],"improved":[195],"predictive":[196],"performance":[197],"while":[198],"providing":[199],"more":[200],"faithful":[201],"compact":[203],"label-conditioned":[204],"explanations.":[205]},"counts_by_year":[],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2026-09-01T00:00:00"}