{"id":"https://openalex.org/W7134894433","doi":"https://doi.org/10.48550/arxiv.2603.09258","title":"Multimodal Graph Representation Learning with Dynamic Information Pathways","display_name":"Multimodal Graph Representation Learning with Dynamic Information Pathways","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134894433","doi":"https://doi.org/10.48550/arxiv.2603.09258"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.09258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09258","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.09258","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128723597","display_name":"Xiaobin Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Xiaobin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101068353","display_name":"Mingkai Lin","orcid":"https://orcid.org/0000-0003-4911-6218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Mingkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128691306","display_name":"Xiaoli Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaoli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128725071","display_name":"Chaoqun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chaoqun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007778753","display_name":"Wenzhong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wenzhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9907000064849854,"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":0.9907000064849854,"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":0.0013000000035390258,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0010999999940395355,"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/embedding","display_name":"Embedding","score":0.5835999846458435},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5429999828338623},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5127999782562256},{"id":"https://openalex.org/keywords/graph-embedding","display_name":"Graph embedding","score":0.5097000002861023},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.43639999628067017},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4244999885559082},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4050999879837036},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.38040000200271606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942000031471252},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5835999846458435},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.5097000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.487199991941452},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47850000858306885},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4244999885559082},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4050999879837036},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.09258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09258","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.09258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09258","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Multimodal":[0],"graphs,":[1],"where":[2],"nodes":[3],"contain":[4],"heterogeneous":[5],"features":[6],"such":[7,21],"as":[8],"images":[9],"and":[10,29,49,60,99,117,131,138],"text,":[11],"are":[12,41],"increasingly":[13],"common":[14],"in":[15,107],"real-world":[16],"applications.":[17],"Effectively":[18],"learning":[19,40,75],"on":[20,51],"graphs":[22],"requires":[23],"both":[24],"adaptive":[25],"intra-modal":[26],"message":[27,90,119],"passing":[28],"efficient":[30,104],"inter-modal":[31],"aggregation.":[32],"However,":[33],"most":[34],"existing":[35],"approaches":[36],"to":[37,135],"multimodal":[38,72],"graph":[39,46,73],"typically":[42],"extended":[43],"from":[44],"conventional":[45],"neural":[47],"networks":[48],"rely":[50],"static":[52],"structures":[53],"or":[54],"dense":[55],"attention,":[56],"which":[57],"limit":[58],"flexibility":[59],"expressive":[61],"node":[62,132],"embedding":[63],"learning.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68],"propose":[69],"a":[70,108],"novel":[71],"representation":[74],"framework":[76],"with":[77,123],"Dynamic":[78],"information":[79,105],"Pathways":[80],"(DiP).":[81],"By":[82],"introducing":[83],"modality-specific":[84],"pseudo":[85],"nodes,":[86],"DiP":[87,151],"enables":[88],"dynamic":[89],"routing":[91],"within":[92],"each":[93],"modality":[94],"via":[95],"proximity-guided":[96],"pseudo-node":[97],"interactions":[98],"captures":[100],"inter-modality":[101],"dependence":[102],"through":[103],"pathways":[106],"shared":[109],"state":[110],"space.":[111],"This":[112],"design":[113],"achieves":[114],"adaptive,":[115],"expressive,":[116],"sparse":[118],"propagation":[120],"across":[121,146],"modalities":[122],"linear":[124],"complexity.":[125],"We":[126],"conduct":[127],"the":[128],"link":[129],"prediction":[130],"classification":[133],"tasks":[134],"evaluate":[136],"performance":[137],"carry":[139],"out":[140],"full":[141],"experimental":[142],"analyses.":[143],"Extensive":[144],"experiments":[145],"multiple":[147],"benchmarks":[148],"demonstrate":[149],"that":[150],"consistently":[152],"outperforms":[153],"baselines.":[154]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-12T00:00:00"}