{"id":"https://openalex.org/W7165166966","doi":"https://doi.org/10.48550/arxiv.2606.18379","title":"RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation","display_name":"RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7165166966","doi":"https://doi.org/10.48550/arxiv.2606.18379"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.18379","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18379","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.2606.18379","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009874448","display_name":"Renzhi Wu","orcid":"https://orcid.org/0000-0002-9144-8999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Renzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136502178","display_name":"Zikun Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Zikun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404947","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0003-4801-7162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125421069","display_name":"Tai Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Tai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138871150","display_name":"Hong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138954087","display_name":"Xian Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138918972","display_name":"Li Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138910072","display_name":"Ke Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108942109","display_name":"Sri Reddy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reddy, Sri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133743105","display_name":"Mahesh Srinivasan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivasan, Mahesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005356160","display_name":"Nipun Mathur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathur, Nipun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138916343","display_name":"Haomin Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Haomin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138845128","display_name":"Hong Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Hong","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":0.7508000135421753,"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":0.7508000135421753,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.041600000113248825,"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"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.041600000113248825,"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/graph","display_name":"Graph","score":0.5566999912261963},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.3986000120639801},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.3953000009059906},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.387800008058548},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.37119999527931213},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.3598000109195709},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3481000065803528},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980999946594238},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.3986000120639801},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36640000343322754},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3481000065803528},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.3043999969959259},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.289000004529953},{"id":"https://openalex.org/C153402090","wikidata":"https://www.wikidata.org/wiki/Q6030480","display_name":"Infomax","level":4,"score":0.2865999937057495},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.18379","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18379","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.2606.18379","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.18379","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":[{"display_name":"Industry, innovation and infrastructure","score":0.6683807969093323,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph-based":[0],"retrieval":[1,44,82,195],"at":[2,34],"billion-node":[3],"scale":[4],"requires":[5,56,92],"jointly":[6],"solving":[7],"three":[8,39],"tightly":[9],"coupled":[10],"problems":[11],"--":[12,20,66,90],"graph":[13,88,172],"construction,":[14],"representation":[15],"learning,":[16],"and":[17,46,135,173,188,191],"real-time":[18],"serving":[19,143],"yet":[21],"existing":[22],"work":[23],"addresses":[24],"each":[25,49],"in":[26],"isolation.":[27],"We":[28],"present":[29],"RankGraph-2,":[30],"a":[31,57,137,152,162,170],"framework":[32],"deployed":[33],"Meta":[35],"that":[36,80,141],"co-designs":[37],"all":[38],"lifecycle":[40,149],"stages":[41],"for":[42,104],"similarity-based":[43,81],"(U2U2I":[45],"U2I2I),":[47],"where":[48],"stage's":[50],"requirements":[51],"shape":[52],"the":[53,72,78],"others.":[54],"Serving":[55],"co-learned":[58],"cluster":[59,139],"index":[60,69,140],"to":[61,94,119,155,185],"avoid":[62],"expensive":[63],"online":[64,87],"KNN":[65],"this":[67,91],"pushes":[68],"co-training":[70],"into":[71],"training":[73],"objective.":[74],"Training":[75],"benefits":[76],"from":[77],"observation":[79],"tolerates":[83],"pre-computed":[84],"neighborhoods,":[85],"eliminating":[86],"infrastructure":[89],"construction":[93],"produce":[95],"self-contained":[96],"data.":[97],"Construction":[98],"must":[99],"also":[100],"support":[101],"hour-level":[102],"refresh":[103],"item":[105,180],"coverage.":[106],"Acting":[107],"on":[108,169,179],"these":[109],"cascading":[110],"requirements,":[111],"RankGraph-2":[112,182],"reduces":[113,142],"hundreds":[114,120],"of":[115,117,121],"trillions":[116],"edges":[118],"billions":[122],"via":[123,132],"subsampling":[124],"with":[125],"popularity":[126],"bias":[127],"correction,":[128],"pre-computes":[129],"multi-hop":[130],"neighborhoods":[131],"personalized":[133],"PageRank,":[134],"co-learns":[136],"residual-quantization":[138],"computational":[144],"cost":[145],"by":[146],"83%.":[147],"This":[148],"co-design":[150],"enables":[151],"simple":[153],"architecture":[154],"achieve":[156],"3.8":[157],"x":[158,175],"higher":[159,176],"recall":[160],"than":[161,177],"GAT":[163],"+":[164],"Deep":[165],"Graph":[166],"Infomax":[167],"model":[168],"bipartite":[171],"2.1":[174],"PyTorch-BigGraph":[178],"retrieval.":[181],"delivers":[183],"up":[184],"+0.96%":[186],"CTR":[187],"+2.75%":[189],"CVR,":[190],"has":[192],"powered":[193],"20+":[194],"launches":[196],"across":[197],"major":[198],"surfaces.":[199]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-19T00:00:00"}