{"id":"https://openalex.org/W7166815835","doi":"https://doi.org/10.18653/v1/2026.findings-acl.890","title":"Not All Modalities at Once: Dynamic Dropout and Bidirectional Fusion for Robust Multi-modal Knowledge Graph Completion","display_name":"Not All Modalities at Once: Dynamic Dropout and Bidirectional Fusion for Robust Multi-modal Knowledge Graph Completion","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166815835","doi":"https://doi.org/10.18653/v1/2026.findings-acl.890"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.890","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.890","pdf_url":"https://aclanthology.org/2026.findings-acl.890.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.890.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134149596","display_name":"Jiashun Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashun Peng","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139773100","display_name":"Fu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Zhang","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139808335","display_name":"Hongzhi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Chen","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139843199","display_name":"Jingwei Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Cheng","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049916719","display_name":"Yingsong Ning","orcid":"https://orcid.org/0000-0003-2182-1978"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingsong Ning","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139740438","display_name":"Xiaoke Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoke Wang","raw_affiliation_strings":["School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering , Northeastern University , Shenyang 110819 , China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80553782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17928","last_page":"17940"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9007999897003174,"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":0.9007999897003174,"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":0.02319999970495701,"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":0.020899999886751175,"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/modalities","display_name":"Modalities","score":0.5332000255584717},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3693999946117401},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.36570000648498535},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.357699990272522},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.34880000352859497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6543999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535099983215332},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3862999975681305},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.890","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.890","pdf_url":"https://aclanthology.org/2026.findings-acl.890.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.890","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.890","pdf_url":"https://aclanthology.org/2026.findings-acl.890.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2799773603","display_name":null,"funder_award_id":"62276057","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166815835.pdf","grobid_xml":"https://content.openalex.org/works/W7166815835.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"Knowledge":[1],"Graph":[2],"Completion":[3],"(MKGC)":[4],"aims":[5],"to":[6,108,117,167],"infer":[7],"missing":[8],"links":[9],"in":[10],"multimodal":[11],"knowledge":[12],"graphs":[13],"by":[14],"leveraging":[15],"structured":[16],"triples":[17],"together":[18],"with":[19,31],"auxiliary":[20,114],"modalities":[21,33,131],"such":[22],"as":[23],"text":[24],"and":[25,46,58,71,116,148,154,185],"images.Existing":[26],"MKGC":[27],"methods":[28],"typically":[29],"train":[30],"all":[32,130],"available,":[34],"implicitly":[35],"assuming":[36],"consistent":[37],"complementarity;":[38],"however,":[39],"this":[40],"practice":[41],"often":[42],"induces":[43],"modality":[44,47,82,96,115],"dependence":[45],"competition":[48],"under":[49,121],"heterogeneous":[50],"noise,":[51],"which":[52],"can":[53],"hinder":[54],"robust":[55],"multi-modal":[56],"fusion":[57,140],"limit":[59],"overall":[60],"performance.To":[61],"address":[62],"these":[63],"issues,":[64],"we":[65,134,158],"propose":[66,159],"MDBGF,":[67],"a":[68,79,137],"Modality":[69],"Dropout":[70],"Bidirectional":[72],"Gated":[73],"Fusion":[74],"framework":[75],"for":[76],"MKGC.MDBGF":[77],"introduces":[78],"dynamic,":[80],"probability-based":[81],"dropout":[83,86,125],"schedule.When":[84],"the":[85,92,102,106,124],"is":[87,126,191],"activated,":[88],"MDBGF":[89],"drops":[90],"either":[91],"textual":[93,147],"or":[94],"visual":[95,149],"during":[97],"training":[98],"while":[99],"always":[100],"preserving":[101],"structural":[103],"information,":[104],"encouraging":[105],"model":[107],"reduce":[109],"over-reliance":[110],"on":[111,172,175],"any":[112],"single":[113],"learn":[118],"complementary":[119],"cues":[120],"missing-modality":[122],"conditions.When":[123],"not":[127],"activated":[128],"(i.e.,":[129],"are":[132],"present),":[133],"further":[135],"design":[136],"bidirectional":[138],"gated":[139],"mechanism":[141],"that":[142,179],"enables":[143],"mutual":[144],"modulation":[145],"between":[146],"modalities,":[150],"enhancing":[151],"cross-modal":[152],"interaction":[153],"flexible":[155],"fusion.In":[156],"addition,":[157],"an":[160],"adaptive":[161],"proportional":[162],"hybrid":[163],"negative":[164],"sampling":[165],"strategy":[166],"strengthen":[168],"MDBGF's":[169],"discriminative":[170],"ability":[171],"hard":[173],"negatives.Experiments":[174],"three":[176],"benchmarks":[177],"show":[178],"MD-BGF":[180],"consistently":[181],"outperforms":[182],"existing":[183],"baselines":[184],"achieves":[186],"new":[187],"state-of-the-art":[188],"results.Our":[189],"code":[190],"available":[192],"at":[193],"https://github.":[194],"com/ferryman-ship/MDBGF.":[195]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}