{"id":"https://openalex.org/W7140200060","doi":"https://doi.org/10.48550/arxiv.2603.20622","title":"Incremental GNN Embedding Computation on Streaming Graphs","display_name":"Incremental GNN Embedding Computation on Streaming Graphs","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7140200060","doi":"https://doi.org/10.48550/arxiv.2603.20622"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.20622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20622","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.20622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wang, Qiange","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qiange","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lv, Haoran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Yanfeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yanfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wong, Weng-Fai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wong, Weng-Fai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"He, Bingsheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Bingsheng","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":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":0.7164999842643738,"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":0.7164999842643738,"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":0.2353000044822693,"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/T14347","display_name":"Big Data and Digital Economy","score":0.005400000140070915,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computation","display_name":"Computation","score":0.7508000135421753},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6431999802589417},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5188000202178955},{"id":"https://openalex.org/keywords/graph-traversal","display_name":"Graph traversal","score":0.4945000112056732},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.4738999903202057},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4307999908924103},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3840999901294708},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.38019999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7836999893188477},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7508000135421753},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6431999802589417},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.6062999963760376},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C96333769","wikidata":"https://www.wikidata.org/wiki/Q907955","display_name":"Graph traversal","level":3,"score":0.4945000112056732},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C184596265","wikidata":"https://www.wikidata.org/wiki/Q2651576","display_name":"Model of computation","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3458999991416931},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C2779377595","wikidata":"https://www.wikidata.org/wiki/Q21045424","display_name":"Approximate Bayesian computation","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.20622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20622","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.20622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20622","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":"Preprint"},"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":{"Graph":[0],"Neural":[1],"Network":[2],"(GNN)":[3],"on":[4,22,86],"streaming":[5,87],"graphs":[6,153],"has":[7],"gained":[8],"increasing":[9],"popularity.":[10],"However,":[11],"its":[12],"practical":[13],"deployment":[14],"remains":[15],"challenging,":[16],"as":[17],"the":[18,48,55,108,119,128,133],"inference":[19],"process":[20,33],"relies":[21],"Runtime":[23],"Embedding":[24],"Computation":[25],"(RTEC)":[26],"to":[27,92,152,167],"capture":[28],"recent":[29],"graph":[30,37,56,60,176],"changes.":[31],"This":[32],"incurs":[34],"heavyweight":[35],"multi-hop":[36],"traversal":[38],"overhead,":[39],"which":[40],"significantly":[41],"undermines":[42],"computation":[43,95,112,136,186],"efficiency.":[44],"We":[45],"observe":[46],"that":[47,164,182],"intermediate":[49],"results":[50],"for":[51,83],"large":[52],"portions":[53],"of":[54,99,132,142],"remain":[57],"unchanged":[58],"during":[59],"evolution,":[61],"and":[62,103,130,178,189],"thus":[63],"redundant":[64],"computations":[65],"can":[66],"be":[67],"effectively":[68],"eliminated":[69],"through":[70],"carefully":[71],"designed":[72],"incremental":[73],"methods.":[74],"In":[75],"this":[76,123],"work,":[77],"we":[78,158],"propose":[79],"an":[80],"efficient":[81,116],"framework":[82,126],"incrementalizing":[84],"RTEC":[85],"graphs.The":[88],"key":[89],"idea":[90],"is":[91],"decouple":[93],"GNN":[94,111,143,179],"into":[96,113],"a":[97,114,139,160],"set":[98],"generalized,":[100],"fine-grained":[101],"operators":[102],"safely":[104],"reorder":[105],"them,":[106],"transforming":[107],"expensive":[109],"full-neighbor":[110,135],"more":[115],"form":[117],"over":[118,193],"affected":[120],"subgraph.":[121],"With":[122],"design,":[124],"our":[125,183],"preserves":[127],"semantics":[129],"accuracy":[131],"original":[134],"while":[137],"supporting":[138],"wide":[140],"range":[141],"models":[144,180],"with":[145,154,170],"complex":[146],"message-passing":[147],"patterns.":[148],"To":[149],"further":[150],"scale":[151],"massive":[155],"historical":[156],"results,":[157],"develop":[159],"GPU-CPU":[161],"co-processing":[162],"system":[163],"offloads":[165],"embeddings":[166],"CPU":[168],"memory":[169],"communication-optimized":[171],"scheduling.":[172],"Experiments":[173],"across":[174],"diverse":[175],"sizes":[177],"show":[181],"method":[184],"reduces":[185],"by":[187],"64%-99%":[188],"achieves":[190],"1.7x-145.8x":[191],"speedups":[192],"existing":[194],"solutions.":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-25T00:00:00"}