{"id":"https://openalex.org/W7125247888","doi":"https://doi.org/10.48550/arxiv.2601.12347","title":"RIPPLE++: An Incremental Framework for Efficient GNN Inference on Evolving Graphs","display_name":"RIPPLE++: An Incremental Framework for Efficient GNN Inference on Evolving Graphs","publication_year":2026,"publication_date":"2026-01-18","ids":{"openalex":"https://openalex.org/W7125247888","doi":"https://doi.org/10.48550/arxiv.2601.12347"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.12347","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.12347","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":null,"license_id":null,"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.2601.12347","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123495304","display_name":"Pranjal Naman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Naman, Pranjal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123498379","display_name":"Parv Agarwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Parv","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092827655","display_name":"Hrishikesh K. Haritas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haritas, Hrishikesh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123490356","display_name":"Yogesh Simmhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simmhan, Yogesh","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5123495304"],"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":0.9695000052452087,"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":0.9695000052452087,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.008200000040233135,"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":0.003700000001117587,"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/inference","display_name":"Inference","score":0.784600019454956},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4984999895095825},{"id":"https://openalex.org/keywords/vertex","display_name":"Vertex (graph theory)","score":0.4675999879837036},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40369999408721924},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3684999942779541},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.3377000093460083},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.296999990940094}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.784600019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232000231742859},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5633999705314636},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.4675999879837036},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C5737132","wikidata":"https://www.wikidata.org/wiki/Q1101814","display_name":"Clique-width","level":5,"score":0.27320000529289246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C47458327","wikidata":"https://www.wikidata.org/wiki/Q910404","display_name":"Random graph","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.12347","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.12347","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.12347","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.12347","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"graphs":[1,175,188],"are":[2,39,73],"dynamic,":[3],"with":[4,195],"frequent":[5],"updates":[6,109,139],"to":[7,13,67,81,113,140,170,213,223],"their":[8,82],"structure":[9,118],"and":[10,16,35,52,107,136,152,160,182,199,217],"features":[11],"due":[12,80],"evolving":[14],"vertex":[15,153],"edge":[17],"properties.":[18],"These":[19,84],"continual":[20],"changes":[21,114],"pose":[22],"significant":[23],"challenges":[24],"for":[25,41,101],"efficient":[26],"inference":[27,37,88,104],"in":[28,57,77,90,111,115],"graph":[29,117,147],"neural":[30],"networks":[31],"(GNNs).":[32],"Existing":[33],"vertex-wise":[34],"layer-wise":[36],"approaches":[38,63],"ill-suited":[40],"dynamic":[42],"graphs,":[43],"as":[44],"they":[45],"incur":[46],"redundant":[47],"computations,":[48],"large":[49],"neighborhood":[50],"traversals,":[51],"high":[53],"communication":[54,220],"costs,":[55],"especially":[56],"distributed":[58,161,208],"settings.":[59],"Additionally,":[60],"while":[61],"sampling-based":[62],"can":[64],"be":[65],"adopted":[66],"approximate":[68],"final":[69],"layer":[70],"embeddings,":[71],"these":[72],"often":[74],"not":[75],"preferred":[76],"critical":[78],"applications":[79],"non-determinism.":[83],"limitations":[85],"hinder":[86],"low-latency":[87],"required":[89],"real-time":[91],"applications.":[92],"To":[93],"address":[94],"this,":[95],"we":[96],"propose":[97],"RIPPLE++,":[98],"a":[99,123,164],"framework":[100],"streaming":[102],"GNN":[103,133],"that":[105,128],"efficiently":[106],"accurately":[108],"embeddings":[110],"response":[112],"the":[116,130],"or":[119],"features.":[120],"RIPPLE++":[121,143,156,210],"introduces":[122],"generalized":[124],"incremental":[125],"programming":[126],"model":[127],"captures":[129],"semantics":[131],"of":[132,197],"aggregation":[134],"functions":[135],"incrementally":[137],"propagates":[138],"affected":[141],"neighborhoods.":[142],"accommodates":[144],"all":[145],"common":[146],"updates,":[148],"including":[149],"vertex/edge":[150],"addition/deletions":[151],"feature":[154],"updates.":[155],"supports":[157],"both":[158],"single-machine":[159],"deployments.":[162],"On":[163],"single":[165],"machine,":[166],"it":[167],"achieves":[168],"up":[169,212],"$56$K":[171],"updates/sec":[172,185],"on":[173,186,205],"sparse":[174],"like":[176,189],"Arxiv":[177],"($169$K":[178],"vertices,":[179,192],"$1.2$M":[180],"edges),":[181,194],"about":[183],"$7.6$K":[184],"denser":[187],"Products":[190],"($2.5$M":[191],"$123.7$M":[193],"latencies":[196],"$0.06$--$960$ms,":[198],"outperforming":[200],"state-of-the-art":[201],"baselines":[202],"by":[203],"$2.2$--$24\\times$":[204],"throughput.":[206],"In":[207],"settings,":[209],"offers":[211],"$\\approx25\\times$":[214],"higher":[215],"throughput":[216],"$20\\times$":[218],"lower":[219],"costs":[221],"compared":[222],"recomputing":[224],"baselines.":[225]},"counts_by_year":[],"updated_date":"2026-01-22T23:33:04.759266","created_date":"2026-01-22T00:00:00"}