{"id":"https://openalex.org/W4416251393","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229162","title":"Kolmogorov-Arnold Network-Enhanced Cross-Modal Alignment for Textual Attribute Graph Reasoning with Large Language Models","display_name":"Kolmogorov-Arnold Network-Enhanced Cross-Modal Alignment for Textual Attribute Graph Reasoning with Large Language Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251393","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229162"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5047056693","display_name":"Qihao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qihao Huang","raw_affiliation_strings":["Southeast University,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Jin","raw_affiliation_strings":["Zhejiang Scientific Research Institute of Transport,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Scientific Research Institute of Transport,Hangzhou,China","institution_ids":["https://openalex.org/I4210127216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101249977","display_name":"Shuke He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuke He","raw_affiliation_strings":["Zhejiang Scientific Research Institute of Transport,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Scientific Research Institute of Transport,Hangzhou,China","institution_ids":["https://openalex.org/I4210127216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lisheng Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lisheng Shu","raw_affiliation_strings":["Zhejiang Scientific Research Institute of Transport,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Scientific Research Institute of Transport,Hangzhou,China","institution_ids":["https://openalex.org/I4210127216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084129061","display_name":"Yaobo Long","orcid":"https://orcid.org/0009-0006-9016-5627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yikang Long","raw_affiliation_strings":["Zhejiang Jiande Institute of General Aviation,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Jiande Institute of General Aviation,Hangzhou,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047056693"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1806232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9703999757766724,"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":0.9703999757766724,"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/T10028","display_name":"Topic Modeling","score":0.014499999582767487,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0020000000949949026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5665000081062317},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.538100004196167},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5306000113487244},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4537000060081482},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41600000858306885},{"id":"https://openalex.org/keywords/graph-embedding","display_name":"Graph embedding","score":0.3986000120639801},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.35429999232292175},{"id":"https://openalex.org/keywords/graph-rewriting","display_name":"Graph rewriting","score":0.3440999984741211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7835999727249146},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5665000081062317},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47870001196861267},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4537000060081482},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.3986000120639801},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2578999996185303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2515434371","https://openalex.org/W2800254025","https://openalex.org/W3025086319","https://openalex.org/W3046819722","https://openalex.org/W3087257704","https://openalex.org/W3092288641","https://openalex.org/W3095319910","https://openalex.org/W3178985330","https://openalex.org/W4312265266","https://openalex.org/W4385568277","https://openalex.org/W4385734218","https://openalex.org/W4387097003","https://openalex.org/W4389523890","https://openalex.org/W4393032075","https://openalex.org/W4393147025","https://openalex.org/W4393277515","https://openalex.org/W4396843991","https://openalex.org/W4396945188","https://openalex.org/W4400524696"],"related_works":[],"abstract_inverted_index":{"Aligning":[0],"structural":[1,66,114],"graph":[2,29,109,134,209,226],"embeddings":[3,135],"with":[4,92,214],"textual":[5,142],"semantics":[6],"is":[7],"crucial":[8],"yet":[9],"challenging":[10],"within":[11,196],"the":[12,63,70,98,119,137,141,164,168,172,203,221],"common":[13],"pipeline":[14,85],"where":[15],"Large":[16,88],"Language":[17,89],"Models":[18,90],"(LLMs)":[19,91],"reason":[20],"over":[21,232],"Textual":[22],"Attribute":[23],"Graphs":[24],"(TAGs)":[25],"informed":[26],"by":[27,86,149],"dedicated":[28],"encoders.":[30],"Traditional":[31],"linear":[32],"alignment":[33,121,166,217],"methods":[34],"are":[35,49],"often":[36],"too":[37],"simplistic":[38],"for":[39,145],"this":[40,55,83,160,197],"task.":[41],"Furthermore,":[42],"while":[43],"standard":[44],"Graph":[45,103],"Neural":[46],"Networks":[47],"(GNNs)":[48],"frequently":[50],"used":[51],"as":[52,106],"encoders":[53,110,210],"in":[54],"pipeline,":[56],"they":[57],"can":[58],"face":[59],"expressiveness":[60],"bottlenecks,":[61],"limiting":[62],"quality":[64],"of":[65,140,206,224],"information":[67],"passed":[68],"to":[69,111,228],"LLM.":[71],"To":[72],"overcome":[73],"these":[74],"limitations,":[75],"we":[76],"propose":[77],"KCA-LLM,":[78],"a":[79,125,130,150],"novel":[80],"framework":[81],"enhancing":[82],"specific":[84],"integrating":[87],"improved":[93],"encoding":[94,99],"and":[95,171],"alignment.":[96],"Addressing":[97],"bottleneck,":[100],"KCA-LLM":[101,191],"employs":[102],"Transformers":[104],"(GTs)":[105],"more":[107,178],"powerful":[108],"capture":[112],"richer":[113],"features":[115],"than":[116,180],"GNNs.":[117],"For":[118],"critical":[120],"step,":[122],"it":[123],"introduces":[124],"two-stage":[126],"adaptive":[127,215],"mechanism:":[128],"first,":[129],"PCA-based":[131],"transformation":[132],"projects":[133],"towards":[136],"principal":[138],"components":[139],"embedding":[143],"space":[144],"initial":[146],"alignment,":[147],"followed":[148],"Kolmogorov-Arnold":[151],"Network":[152],"(KAN)":[153],"projector.":[154],"Leveraging":[155],"KAN\u2019s":[156],"learnable":[157],"activation":[158],"functions,":[159],"projector":[161],"dynamically":[162],"adapts":[163],"fine-grained":[165],"between":[167],"encoder":[169],"output":[170],"LLM\u2019s":[173],"expected":[174],"input":[175],"space,":[176],"offering":[177],"flexibility":[179],"fixed":[181],"MLP-based":[182],"approaches.":[183],"Experiments":[184],"on":[185,220],"three":[186],"large-scale":[187],"TAG":[188],"benchmarks":[189],"show":[190],"achieves":[192],"state-of-the-art":[193],"reasoning":[194,198,231],"accuracy":[195],"paradigm.":[199],"Our":[200],"findings":[201],"highlight":[202],"significant":[204],"impact":[205],"employing":[207],"advanced":[208],"(like":[211,218],"GTs)":[212],"coupled":[213],"cross-modal":[216],"PCA-KAN)":[219],"overall":[222],"effectiveness":[223],"using":[225],"representations":[227],"inform":[229],"LLM":[230],"TAGs.":[233]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-11-14T00:00:00"}