{"id":"https://openalex.org/W4416034138","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1270","title":"HomoGraphAdapter: A Homogeneous Graph Neural Network as an Effective Adapter for Vision-Language Models","display_name":"HomoGraphAdapter: A Homogeneous Graph Neural Network as an Effective Adapter for Vision-Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034138","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1270"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1270","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","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/A5091114864","display_name":"Chuan He","orcid":"https://orcid.org/0000-0003-4319-7424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuan He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087300252","display_name":"Zhuozhao Li","orcid":"https://orcid.org/0000-0003-1903-6428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuozhao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100987784","display_name":"Song Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071544774","display_name":"Xiaocheng Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaocheng Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057352675","display_name":"Jinxiang Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinxiang Lai","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":"23400","last_page":"23414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.00279999990016222,"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":0.002199999988079071,"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/leverage","display_name":"Leverage (statistics)","score":0.5105000138282776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5044000148773193},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4779999852180481},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4758000075817108},{"id":"https://openalex.org/keywords/precomputation","display_name":"Precomputation","score":0.45750001072883606},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.4553999900817871},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.35839998722076416},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.35830000042915344},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.3269999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287999987602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5745999813079834},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5044000148773193},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C159379195","wikidata":"https://www.wikidata.org/wiki/Q7239568","display_name":"Precomputation","level":3,"score":0.45750001072883606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45570001006126404},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.349700003862381},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1270","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169001","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169001","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs),":[2],"such":[3],"as":[4],"CLIP,":[5],"have":[6],"exhibited":[7],"significant":[8],"advancements":[9],"in":[10],"recognizing":[11],"visual":[12,77],"concepts":[13],"through":[14],"natural":[15],"language":[16],"guidance.":[17],"However,":[18],"adapting":[19],"these":[20],"models":[21],"to":[22,52,106],"downstream":[23],"tasks":[24],"remains":[25],"challenging.":[26],"Existing":[27],"adaptation":[28],"methods":[29],"either":[30],"overlook":[31],"the":[32,36,121,131],"structural":[33],"knowledge":[34],"between":[35,89],"text":[37,113],"and":[38,56,76,86,93,109,114,126,146,159],"image":[39,115],"modalities":[40],"or":[41],"create":[42],"overly":[43],"complex":[44],"graphs":[45],"containing":[46],"redundant":[47],"information":[48],"for":[49,91,123,144,148],"alignment,":[50],"leading":[51],"suboptimal":[53],"classification":[54,125,137],"performance":[55,122],"increased":[57],"computational":[58],"overhead.":[59],"This":[60],"paper":[61],"proposes":[62],"a":[63,80,99],"novel":[64],"adapter-tuning":[65],"methodology":[66],"named":[67],"Homogeneous":[68],"Graph":[69,102],"Adapter":[70],"(HomoGraphAdapter),":[71],"which":[72],"transforms":[73],"diverse":[74],"textual":[75],"descriptions":[78],"into":[79],"unified":[81],"set":[82],"of":[83,142],"node":[84],"representations":[85],"establishes":[87],"edges":[88],"nodes":[90],"inter-modal":[92],"cross-modal":[94],"semantic":[95],"alignment.":[96],"We":[97],"leverage":[98],"straightforward":[100],"homogeneous":[101],"Neural":[103],"Network":[104],"(GNN)":[105],"adapt":[107],"positive":[108],"negative":[110],"classifiers":[111,118],"across":[112],"modalities.":[116],"The":[117],"comprehensively":[119],"enhance":[120],"few-shot":[124],"OOD":[127],"generalization.":[128],"Compared":[129],"with":[130],"SOTA":[132],"approach":[133],"HeGraphAdapter,":[134],"HomoGraphAdapter":[135],"improves":[136],"accuracy":[138],"by":[139],"an":[140],"average":[141],"1.51%":[143],"1-shot":[145],"0.74%":[147],"16-shot":[149],"on":[150],"11":[151],"datasets,":[152],"while":[153],"also":[154],"reducing":[155],"both":[156],"precomputation":[157],"time":[158],"training":[160],"time.":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}