{"id":"https://openalex.org/W7131669826","doi":"https://doi.org/10.1109/ickg66886.2025.00054","title":"DMF-MH:Dual-Stage Modality-Aware Fusion for Modality Heterogeneity in Multimodal Knowledge Graph Completion","display_name":"DMF-MH:Dual-Stage Modality-Aware Fusion for Modality Heterogeneity in Multimodal Knowledge Graph Completion","publication_year":2025,"publication_date":"2025-11-13","ids":{"openalex":"https://openalex.org/W7131669826","doi":"https://doi.org/10.1109/ickg66886.2025.00054"},"language":null,"primary_location":{"id":"doi:10.1109/ickg66886.2025.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ickg66886.2025.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Knowledge Graph (ICKG)","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/A5126880334","display_name":"Ronghua Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghua Tian","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Chongqing Key Laboratory of Computational Intelligence,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Chongqing Key Laboratory of Computational Intelligence,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126881920","display_name":"Hong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Yu","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Chongqing Key Laboratory of Computational Intelligence,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Chongqing Key Laboratory of Computational Intelligence,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81543131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"363","last_page":"370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.920799970626831,"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":0.920799970626831,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.010099999606609344,"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/T10028","display_name":"Topic Modeling","score":0.009999999776482582,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6323999762535095},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6144999861717224},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.545199990272522},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5148000121116638},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.498199999332428},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.39500001072883606},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3774999976158142},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.33219999074935913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490000128746033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6521000266075134},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6323999762535095},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6144999861717224},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.545199990272522},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4343000054359436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4336000084877014},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3774999976158142},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ickg66886.2025.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ickg66886.2025.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Knowledge Graph (ICKG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2759494219","display_name":null,"funder_award_id":"62136002,62221005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1552847225","https://openalex.org/W2022166150","https://openalex.org/W2080133951","https://openalex.org/W2526174222","https://openalex.org/W2759136286","https://openalex.org/W2807480793","https://openalex.org/W2889583850","https://openalex.org/W2945623882","https://openalex.org/W2963606508","https://openalex.org/W2963870853","https://openalex.org/W2979129662","https://openalex.org/W3172335055","https://openalex.org/W3175989614","https://openalex.org/W3202813375","https://openalex.org/W3207311065","https://openalex.org/W4225412853","https://openalex.org/W4252707176","https://openalex.org/W4304091767","https://openalex.org/W4353007065","https://openalex.org/W4380303532","https://openalex.org/W4385482714","https://openalex.org/W4385568031","https://openalex.org/W4385573706","https://openalex.org/W4386057717","https://openalex.org/W4387967963","https://openalex.org/W4389520035","https://openalex.org/W4400111732"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Knowledge":[1],"Graph":[2],"Completion":[3],"(MMKGC)":[4],"aims":[5],"to":[6,60,74,89],"infer":[7],"missing":[8],"knowledge":[9,12],"in":[10,38,64],"multimodal":[11,17],"graphs":[13],"(MMKGs)":[14],"enriched":[15],"with":[16,86],"entity":[18],"representations":[19],"such":[20],"as":[21],"textual":[22],"descriptions":[23],"and":[24,43,79,126,143],"images.":[25],"However,":[26],"the":[27,67,100,104,115],"intrinsic":[28],"heterogeneity":[29,63],"across":[30],"modalities":[31,98],"poses":[32],"a":[33,53,81,109],"significant":[34],"challenge,":[35],"often":[36],"resulting":[37],"semantic":[39,77],"inconsistency,":[40],"representation":[41],"misalignment,":[42],"modality":[44,62,119,150],"conflict.":[45],"To":[46],"address":[47],"these":[48],"issues,":[49],"we":[50,70,107],"propose":[51],"DMF-MH,":[52],"Dual-stage":[54],"Modality-aware":[55],"Fusion":[56],"framework":[57],"specifically":[58],"designed":[59],"mitigate":[61],"MMKGC.":[65],"In":[66,103],"first":[68],"stage,":[69,106],"employ":[71],"modality-specific":[72],"encoders":[73],"extract":[75],"independent":[76],"features,":[78],"utilize":[80],"bilinear":[82],"fusion":[83,111],"mechanism":[84],"combined":[85],"contrastive":[87],"learning":[88],"explicitly":[90],"model":[91],"cross-modal":[92],"interactions":[93],"while":[94],"enforcing":[95],"alignment":[96],"between":[97],"of":[99,117],"same":[101],"entity.":[102],"second":[105],"implement":[108],"decision-level":[110],"strategy":[112],"that":[113,136],"integrates":[114],"predictions":[116],"each":[118],"using":[120],"learned":[121],"reliability-aware":[122],"weights,":[123],"enabling":[124],"robust":[125],"adaptive":[127],"inference.":[128],"Extensive":[129],"experiments":[130],"on":[131],"three":[132],"public":[133],"datasets":[134],"demonstrate":[135],"DMF-MH":[137],"significantly":[138],"improves":[139],"link":[140],"prediction":[141],"performance":[142],"exhibits":[144],"strong":[145],"generalization":[146],"ability":[147],"under":[148],"heterogeneous":[149],"settings.":[151]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-02-27T00:00:00"}