{"id":"https://openalex.org/W7155078717","doi":"https://doi.org/10.48550/arxiv.2604.18351","title":"Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems","display_name":"Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155078717","doi":"https://doi.org/10.48550/arxiv.2604.18351"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.18351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18351","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.2604.18351","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134189258","display_name":"Runhao Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Runhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040420455","display_name":"Renchi Yang","orcid":"https://orcid.org/0000-0002-7284-3096"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Renchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100982809","display_name":"Donghao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Donghao","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.35260000824928284,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.35260000824928284,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.18289999663829803,"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":0.05380000174045563,"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/embedding","display_name":"Embedding","score":0.8418999910354614},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6930000185966492},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5825999975204468},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.567300021648407},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5246999859809875},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4810999929904938},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4343000054359436}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8418999910354614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345999717712402},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6930000185966492},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5825999975204468},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5246999859809875},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3919999897480011},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.18351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18351","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.2604.18351","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18351","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recommender":[0],"systems":[1],"have":[2],"advanced":[3],"markedly":[4],"over":[5,195,205],"the":[6,99,118,122,146,218],"past":[7],"decade":[8],"by":[9,28,204,221],"transforming":[10],"each":[11],"user/item":[12],"into":[13,145],"a":[14,35,82,127,165,208],"dense":[15],"embedding":[16,25,60,89,202],"vector":[17],"with":[18,164,207],"deep":[19],"learning":[20],"models.":[21],"At":[22],"industrial":[23],"scale,":[24],"tables":[26],"constituted":[27],"such":[29,113],"vectors":[30],"of":[31,38,101,210],"all":[32],"users/items":[33,116],"demand":[34],"vast":[36],"amount":[37],"parameters":[39,203],"and":[40,44,49,84,110,139,171,192],"impose":[41],"heavy":[42],"compute":[43],"memory":[45],"overhead":[46],"during":[47],"training":[48],"inference,":[50],"hindering":[51],"model":[52],"deployment":[53],"under":[54],"resource":[55],"constraints.":[56],"Existing":[57],"solutions":[58],"towards":[59],"compression":[61],"either":[62],"suffer":[63],"from":[64],"severely":[65],"compromised":[66],"recommendation":[67],"accuracy":[68],"or":[69],"incur":[70],"considerable":[71],"computational":[72],"costs.":[73],"To":[74,152],"mitigate":[75],"these":[76],"issues,":[77],"this":[78,162],"paper":[79],"presents":[80],"BACO,":[81],"fast":[83],"effective":[85,154],"framework":[86,147,163],"for":[87,108,169],"compressing":[88],"tables.":[90],"Unlike":[91],"traditional":[92],"ID":[93],"hashing,":[94],"BACO":[95,160,188,200],"is":[96],"built":[97],"on":[98],"idea":[100],"exploiting":[102],"collaborative":[103],"signals":[104],"in":[105,121,214],"user-item":[106],"interactions":[107],"user":[109,182],"item":[111],"groupings,":[112],"that":[114,131,199],"similar":[115],"share":[117],"same":[119],"embeddings":[120],"codebook.":[123],"Specifically,":[124],"we":[125],"formulate":[126],"balanced":[128],"co-clustering":[129],"objective":[130],"maximizes":[132],"intra-cluster":[133],"connectivity":[134],"while":[135,156,216],"enforcing":[136],"cluster-volume":[137],"balance,":[138],"unify":[140],"canonical":[141],"graph":[142],"clustering":[143],"techniques":[144],"through":[148],"rigorous":[149],"theoretical":[150],"analyses.":[151],"produce":[153],"groupings":[155],"averting":[157],"codebook":[158],"collapse,":[159],"instantiates":[161],"principled":[166],"weighting":[167],"scheme":[168],"users":[170],"items,":[172],"an":[173],"efficient":[174],"label":[175],"propagation":[176],"solver,":[177],"as":[178,180],"well":[179],"secondary":[181],"clusters.":[183],"Our":[184],"extensive":[185],"experiments":[186],"comparing":[187],"against":[189],"full":[190],"models":[191],"18":[193],"baselines":[194,220],"benchmark":[196],"datasets":[197],"demonstrate":[198],"cuts":[201],"75%":[206],"drop":[209],"at":[211],"most":[212],"1.85%":[213],"recall,":[215],"surpassing":[217],"strongest":[219],"being":[222],"up":[223],"to":[224],"346X":[225],"faster.":[226]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-22T00:00:00"}