{"id":"https://openalex.org/W7116847132","doi":"https://doi.org/10.1631/fitee.2500429","title":"GMCoT: a graph-augmented multimodal chain-of-thought reasoning framework for multi-label zero-shot learning","display_name":"GMCoT: a graph-augmented multimodal chain-of-thought reasoning framework for multi-label zero-shot learning","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7116847132","doi":"https://doi.org/10.1631/fitee.2500429"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2500429","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2500429","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-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/A5121076216","display_name":"Xiang Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Wen","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121072175","display_name":"Haobo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobo Wang","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Hangzhou, 310027, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Hangzhou, 310027, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121102299","display_name":"Ke Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","institution_ids":["https://openalex.org/I1328775524"]},{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121043648","display_name":"Tianlei Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlei Hu","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","institution_ids":["https://openalex.org/I1328775524"]},{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121109204","display_name":"Gang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Chen","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China"],"raw_orcid":"https://orcid.org/0000-0002-7483-0045","affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","institution_ids":["https://openalex.org/I1328775524"]},{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, 310027, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5121109204"],"corresponding_institution_ids":["https://openalex.org/I1328775524","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79681214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"12","first_page":"2623","last_page":"2637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.6338000297546387,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.6338000297546387,"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":0.10409999638795853,"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":0.09160000085830688,"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/benchmark","display_name":"Benchmark (surveying)","score":0.5317000150680542},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5295000076293945},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5121999979019165},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4172999858856201},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.38850000500679016},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.3521000146865845},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.34150001406669617},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3296999931335449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494999766349792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6875},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4537000060081482},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3172999918460846},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2500429","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2500429","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6921785473823547}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W64813323","https://openalex.org/W80699098","https://openalex.org/W1514027499","https://openalex.org/W1576514601","https://openalex.org/W1999818274","https://openalex.org/W1999954155","https://openalex.org/W2007972815","https://openalex.org/W2027869746","https://openalex.org/W2064675550","https://openalex.org/W2119466907","https://openalex.org/W2128532956","https://openalex.org/W2131774270","https://openalex.org/W2146241755","https://openalex.org/W2171061940","https://openalex.org/W2247565594","https://openalex.org/W2255924030","https://openalex.org/W2289084343","https://openalex.org/W2413850928","https://openalex.org/W2463598282","https://openalex.org/W2596142952","https://openalex.org/W2604675517","https://openalex.org/W2932399282","https://openalex.org/W2953000611","https://openalex.org/W2962762077","https://openalex.org/W2963052338","https://openalex.org/W2963513598","https://openalex.org/W2963745697","https://openalex.org/W2964086552","https://openalex.org/W3034978279","https://openalex.org/W3143107425","https://openalex.org/W3163811911","https://openalex.org/W3167456680","https://openalex.org/W3184087575","https://openalex.org/W3202858701","https://openalex.org/W3216083537","https://openalex.org/W4221161695","https://openalex.org/W4288083516","https://openalex.org/W4291311341","https://openalex.org/W4298333097","https://openalex.org/W4316135748","https://openalex.org/W4319165821","https://openalex.org/W4372267073","https://openalex.org/W4382450414","https://openalex.org/W4384306363","https://openalex.org/W4385825703","https://openalex.org/W4390190073","https://openalex.org/W4390689965","https://openalex.org/W4404199100","https://openalex.org/W4406523182","https://openalex.org/W6891831295","https://openalex.org/W6910671462"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"multi-label":[3,130,148,181],"zero-shot":[4],"learning":[5,51],"(ML-ZSL)":[6],"has":[7],"garnered":[8],"increasing":[9],"attention":[10],"because":[11],"of":[12,16,115,168,180],"its":[13],"wide":[14],"range":[15],"potential":[17],"applications,":[18],"such":[19],"as":[20],"image":[21],"annotation,":[22],"text":[23],"classification,":[24],"and":[25,74,77,93,178],"bioinformatics.":[26],"The":[27,109],"central":[28],"challenge":[29],"in":[30,33,90,129,197],"ML-ZSL":[31],"lies":[32],"predicting":[34],"multiple":[35,82],"labels":[36],"for":[37,155],"unseen":[38],"classes":[39],"without":[40],"requiring":[41],"any":[42],"labeled":[43],"training":[44],"data,":[45],"which":[46,69,141],"contrasts":[47],"with":[48,120],"conventional":[49],"supervised":[50],"paradigms.":[52],"However,":[53],"existing":[54],"methods":[55,196],"face":[56],"several":[57],"significant":[58],"challenges.":[59],"These":[60],"include":[61],"the":[62,75,113,125,160,166,176,190],"substantial":[63],"semantic":[64,170],"gap":[65],"between":[66],"different":[67],"modalities,":[68],"impedes":[70],"effective":[71],"knowledge":[72],"transfer,":[73],"intricate":[76],"typically":[78],"complex":[79,169],"relationships":[80,171],"among":[81,172],"labels,":[83,173],"making":[84],"it":[85],"difficult":[86],"to":[87,146],"model":[88],"them":[89],"a":[91,102,133,151],"meaningful":[92],"accurate":[94],"manner.":[95],"To":[96],"overcome":[97],"these":[98],"challenges,":[99],"we":[100],"propose":[101],"graph-augmented":[103],"multimodal":[104,116,135],"chain-of-thought":[105,136],"(GMCoT)":[106],"reasoning":[107,126,137,145,161],"approach.":[108],"proposed":[110,191],"method":[111],"combines":[112],"strengths":[114],"large":[117],"language":[118],"models":[119],"graph-based":[121],"structures,":[122],"significantly":[123],"enhancing":[124],"process":[127],"involved":[128],"prediction.":[131],"First,":[132],"novel":[134],"framework":[138],"is":[139,153],"presented":[140,154],"imitates":[142],"human-like":[143],"step-by-step":[144],"produce":[147],"predictions.":[149],"Second,":[150],"technique":[152,164],"integrating":[156],"label":[157],"graphs":[158],"into":[159],"process.":[162],"This":[163],"enables":[165],"capture":[167],"thereby":[174],"improving":[175],"accuracy":[177],"consistency":[179],"generation.":[182],"Comprehensive":[183],"experiments":[184],"on":[185],"benchmark":[186],"datasets":[187],"demonstrate":[188],"that":[189],"GMCoT":[192],"approach":[193],"outperforms":[194],"state-of-the-art":[195],"ML-ZSL.":[198]},"counts_by_year":[],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-12-23T00:00:00"}