{"id":"https://openalex.org/W7170466226","doi":"https://doi.org/10.48550/arxiv.2607.20737","title":"Cardinality-Decomposed Loss: Matching Training Objectives to Relation Structure in Heterogeneous Recommendation Graphs","display_name":"Cardinality-Decomposed Loss: Matching Training Objectives to Relation Structure in Heterogeneous Recommendation Graphs","publication_year":2026,"publication_date":"2026-07-22","ids":{"openalex":"https://openalex.org/W7170466226","doi":"https://doi.org/10.48550/arxiv.2607.20737"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.20737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20737","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":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.2607.20737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114061695","display_name":"P and S. Jaya Prabhavathi G. Gayathry Maheshwari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maheshwari, Parul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143543546","display_name":"Amulya Paruchuri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paruchuri, Amulya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113916601","display_name":"Yiqing Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Yiqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070491230","display_name":"Alireza Sahami Shirazi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shirazi, Alireza Sahami","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121592494","display_name":"Farhad Farahani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farahani, Farhad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143573514","display_name":"Prakhar Mehrotra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehrotra, Prakhar","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":0.8827999830245972,"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":0.8827999830245972,"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":0.05339999869465828,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.013100000098347664,"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/bipartite-graph","display_name":"Bipartite graph","score":0.6808000206947327},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4657999873161316},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4465999901294708},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42800000309944153},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42329999804496765},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.40939998626708984},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.40860000252723694},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.4041000008583069},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3783999979496002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289000153541565},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.6808000206947327},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43540000915527344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4336000084877014},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4284000098705292},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4205999970436096},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C47458327","wikidata":"https://www.wikidata.org/wiki/Q910404","display_name":"Random graph","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C29143872","wikidata":"https://www.wikidata.org/wiki/Q876690","display_name":"Business process reengineering","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.20737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20737","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":"doi:10.48550/arxiv.2607.20737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20737","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.72287917137146,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"trained":[3],"on":[4,160,170,180],"heterogenous":[5],"bipartite":[6],"graphs":[7,16],"form":[8],"a":[9,36,76,117,219,227],"common":[10],"basis":[11],"in":[12,22,93,151,192],"recommendation":[13,61],"systems.":[14],"These":[15],"often":[17,50],"express":[18],"relations":[19,137],"that":[20,65,79,121,187,198,230],"vary":[21],"cardinality,":[23],"for":[24,42,59,136],"example,":[25],"user-item":[26],"preferences":[27],"are":[28,33,100],"one-to-many":[29],"and":[30,86,127,179,185,226,242],"user-attribute":[31],"features":[32],"one-to-one.":[34],"Traditionally,":[35],"unique":[37],"loss":[38],"function":[39],"is":[40,49,215,233],"applied":[41],"all":[43],"of":[44],"the":[45,60,131,147,152,213,249,258],"network":[46],"components":[47],"which":[48,99],"Bayesian":[51],"Personalized":[52],"Ranking":[53],"(BPR).":[54],"While":[55],"BPR":[56,128],"works":[57],"well":[58],"task,":[62],"we":[63,115],"find":[64,186],"it":[66,211],"causes":[67],"attribute":[68,193,250],"embeddings":[69],"to":[70,72,89,129,133,222],"collapse":[71],"near-random":[73],"geometry":[74],"--":[75,167,184,239],"silent":[77],"failure":[78],"leaves":[80],"standard":[81],"ranking":[82,199],"metrics":[83],"largely":[84],"unaffected":[85],"therefore":[87],"invisible":[88],"conventional":[90],"evaluation.":[91],"This":[92],"turn":[94],"pollutes":[95],"user":[96,171],"node":[97],"embeddings,":[98],"shaped":[101],"by":[102,145,235],"both":[103,123],"edge":[104],"types":[105],"simultaneously,":[106],"hurting":[107],"downstream":[108],"tasks":[109],"like":[110],"personalization,":[111],"segmentation,":[112],"etc.":[113],"Here":[114],"propose":[116],"Cardinality-Decomposed":[118],"Loss":[119],"(CDL)":[120],"combines":[122],"Cross":[124],"Entropy":[125],"(CE)":[126],"enable":[130],"model":[132],"collectively":[134],"optimize":[135],"across":[138],"cardinalities.":[139],"We":[140,157,195,217],"confirm":[141],"this":[142,224],"CE-BPR":[143],"conflict":[144],"showing":[146],"two":[148,164,236],"losses":[149],"compete":[150],"shared":[153],"encoder's":[154],"parameter":[155,221],"space.":[156],"evaluate":[158],"CDL":[159,188],"five":[161],"datasets":[162],"spanning":[163],"structural":[165],"configurations":[166],"one-to-one":[168],"attributes":[169,203],"nodes":[172,182],"(MovieLens-1M,":[173],"Last.fm-360K,":[174],"PayPal":[175],"Audience":[176],"Factory,":[177],"BookCrossing)":[178],"item":[181],"(Yelp)":[183],"consistently":[189],"improves":[190,201],"discriminability":[191],"embeddings.":[194],"also":[196],"show":[197],"(NDCG)":[200],"when":[202,212],"carry":[204],"meaningful":[205],"preference":[206],"signal,":[207],"but":[208],"conflicts":[209],"with":[210],"correlation":[214],"weak.":[216],"use":[218],"lambda":[220],"navigate":[223],"trade-off,":[225],"lambda-sweep":[228],"reveals":[229],"dataset":[231],"behavior":[232],"governed":[234],"graph":[237],"properties":[238],"semantic":[240],"alignment":[241,246],"topology":[243,254],"leakage.":[244],"Semantic":[245],"measures":[247,256],"whether":[248,257],"predicts":[251],"preferences,":[252],"while":[253],"leakage":[255],"graph's":[259],"connectivity":[260],"already":[261],"encodes":[262],"it.":[263]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-25T00:00:00"}