{"id":"https://openalex.org/W4400104368","doi":"https://doi.org/10.48550/arxiv.2406.17894","title":"Efficient and Effective Implicit Dynamic Graph Neural Network","display_name":"Efficient and Effective Implicit Dynamic Graph Neural Network","publication_year":2024,"publication_date":"2024-06-25","ids":{"openalex":"https://openalex.org/W4400104368","doi":"https://doi.org/10.48550/arxiv.2406.17894"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.17894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.17894","pdf_url":"https://arxiv.org/pdf/2406.17894","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.17894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109387639","display_name":"Yongjian Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yongjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102889089","display_name":"Hieu M. Vu","orcid":"https://orcid.org/0009-0004-2200-1319"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vu, Hieu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023288846","display_name":"Tianbao Yang","orcid":"https://orcid.org/0000-0002-7858-5438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Tianbao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052463345","display_name":"Bijaya Adhikari","orcid":"https://orcid.org/0000-0001-8409-8073"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adhikari, Bijaya","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":true,"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":0.9225000143051147,"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":0.9225000143051147,"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/T10320","display_name":"Neural Networks and Applications","score":0.9059000015258789,"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/computer-science","display_name":"Computer science","score":0.5950309634208679},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48149001598358154},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48107457160949707},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3216574192047119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31536686420440674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5950309634208679},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48149001598358154},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48107457160949707},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3216574192047119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31536686420440674}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.17894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.17894","pdf_url":"https://arxiv.org/pdf/2406.17894","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.17894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.17894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.17894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.17894","pdf_url":"https://arxiv.org/pdf/2406.17894","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400104368.pdf","grobid_xml":"https://content.openalex.org/works/W4400104368.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Implicit":[0,72],"graph":[1,60],"neural":[2,61,81],"networks":[3],"have":[4,110,142],"gained":[5],"popularity":[6],"in":[7,19,41,63,131,146],"recent":[8],"years":[9],"as":[10,44,135],"they":[11],"capture":[12],"long-range":[13,36],"dependencies":[14],"while":[15,221],"improving":[16],"predictive":[17],"performance":[18,26,215],"static":[20],"graphs.":[21],"Despite":[22],"the":[23,30,88,118,179,196,202,214,217],"tussle":[24],"between":[25],"degradation":[27],"due":[28],"to":[29,109,124,143,194,224],"oversmoothing":[31],"of":[32,90,96,175,178,198,216],"learned":[33],"embeddings":[34],"and":[35,51,160,191],"dependency":[37],"being":[38],"more":[39],"pronounced":[40],"dynamic":[42,65,84,133],"graphs,":[43],"features":[45],"are":[46],"aggregated":[47],"both":[48,189],"across":[49],"neighborhood":[50],"time,":[52],"no":[53],"prior":[54],"work":[55],"has":[56],"proposed":[57],"an":[58,147,155,162],"implicit":[59,80,126],"model":[62],"a":[64,78,111],"setting.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,153],"present":[71],"Dynamic":[73],"Graph":[74],"Neural":[75],"Network":[76],"(IDGNN)":[77],"novel":[79],"network":[82],"for":[83],"graphs":[85],"which":[86,140],"is":[87,98,102,106,128],"first":[89],"its":[91],"kind.":[92],"A":[93],"key":[94,176],"characteristic":[95],"IDGNN":[97],"that":[99,117,167,208],"it":[100,105,136],"demonstrably":[101],"well-posed,":[103],"i.e.,":[104],"theoretically":[107],"guaranteed":[108],"fixed-point":[112],"representation.":[113],"We":[114,181,205],"then":[115],"demonstrate":[116,195,207],"standard":[119],"iterative":[120,148,169,219],"algorithm":[121,166,220],"often":[122],"used":[123],"train":[125],"models":[127],"computationally":[129],"expensive":[130,218],"our":[132,199,209],"setting":[134],"involves":[137],"computing":[138],"gradients,":[139],"themselves":[141],"be":[144],"estimated":[145],"manner.":[149],"To":[150],"overcome":[151],"this,":[152],"pose":[154],"equivalent":[156],"bilevel":[157],"optimization":[158,211],"problem":[159],"propose":[161],"efficient":[163],"single-loop":[164],"training":[165],"avoids":[168],"computation":[170],"by":[171],"maintaining":[172],"moving":[173],"averages":[174],"components":[177],"gradients.":[180],"conduct":[182],"extensive":[183],"experiments":[184],"on":[185,188],"real-world":[186],"datasets":[187],"classification":[190],"regression":[192],"tasks":[193],"superiority":[197],"approach":[200],"over":[201],"state-of-the-art":[203],"baselines.":[204],"also":[206],"bi-level":[210],"framework":[212],"maintains":[213],"obtaining":[222],"up":[223],"\\textbf{1600x}":[225],"speed-up.":[226]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}