{"id":"https://openalex.org/W4378711628","doi":"https://doi.org/10.1145/3580305.3599834","title":"Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems","display_name":"Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4378711628","doi":"https://doi.org/10.1145/3580305.3599834"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599834","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599834","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100375161","display_name":"Xiaohui Chen","orcid":"https://orcid.org/0000-0002-2020-5340"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohui Chen","raw_affiliation_strings":["Tufts University, Medford, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2020-5340","affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424691","display_name":"Jiankai Sun","orcid":"https://orcid.org/0000-0002-7214-0665"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiankai Sun","raw_affiliation_strings":["ByteDance Inc., Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7214-0665","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037489400","display_name":"Taiqing Wang","orcid":"https://orcid.org/0000-0002-3233-2208"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taiqing Wang","raw_affiliation_strings":["ByteDance Inc., Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3233-2208","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054719216","display_name":"Ruocheng Guo","orcid":"https://orcid.org/0000-0002-8522-6142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruocheng Guo","raw_affiliation_strings":["ByteDance Research, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8522-6142","affiliations":[{"raw_affiliation_string":"ByteDance Research, London, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352436","display_name":"Liping Liu","orcid":"https://orcid.org/0000-0002-3690-3928"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Ping Liu","raw_affiliation_strings":["Tufts University, Medford, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3690-3928","affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":null,"display_name":"Aonan Zhang","orcid":"https://orcid.org/0009-0005-1952-604X"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aonan Zhang","raw_affiliation_strings":["Apple Inc., Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0005-1952-604X","affiliations":[{"raw_affiliation_string":"Apple Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.828,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76908461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3865","last_page":"3876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9991999864578247,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9713000059127808,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8088973760604858},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.588451087474823},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5235654711723328},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.518812358379364},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.45521870255470276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3837628662586212},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38117051124572754},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37363699078559875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088973760604858},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.588451087474823},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5235654711723328},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.518812358379364},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.45521870255470276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3837628662586212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38117051124572754},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37363699078559875},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3580305.3599834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599834","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.16391","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.16391","pdf_url":"https://arxiv.org/pdf/2305.16391","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599834","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599834","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378711628.pdf","grobid_xml":"https://content.openalex.org/works/W4378711628.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W837061932","https://openalex.org/W2020144485","https://openalex.org/W2055935910","https://openalex.org/W2102035799","https://openalex.org/W2125664420","https://openalex.org/W2475334473","https://openalex.org/W2603119212","https://openalex.org/W2619206542","https://openalex.org/W2640408555","https://openalex.org/W2807021761","https://openalex.org/W2954808392","https://openalex.org/W2963239847","https://openalex.org/W2963323306","https://openalex.org/W2963794747","https://openalex.org/W3034503922","https://openalex.org/W3035909655","https://openalex.org/W3036320503","https://openalex.org/W3040405911","https://openalex.org/W3043437699","https://openalex.org/W3081190557","https://openalex.org/W3083784942","https://openalex.org/W3098468692","https://openalex.org/W3098488568","https://openalex.org/W3100848837","https://openalex.org/W3101023724","https://openalex.org/W3103345676","https://openalex.org/W3158114995","https://openalex.org/W3165893786","https://openalex.org/W3211185553","https://openalex.org/W3212448405","https://openalex.org/W4233471163"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W2056712470","https://openalex.org/W3125580266","https://openalex.org/W4288390103","https://openalex.org/W4317039510","https://openalex.org/W4238861846"],"abstract_inverted_index":{"Data":[0],"subsampling":[1,15,42,59,127],"is":[2,39,48,115],"widely":[3],"used":[4,144],"to":[5,26,79,104,162],"speed":[6],"up":[7],"the":[8,36,73,76,81,90,102,107,120,134,143],"training":[9],"of":[10,75,83,122],"large-scale":[11],"recommendation":[12,52],"systems.":[13],"Most":[14],"methods":[16,43,60,157],"are":[17],"model-based":[18,41,126],"and":[19,125,150],"often":[20],"require":[21],"a":[22,98],"pre-trained":[23],"pilot":[24,37],"model":[25,38,46],"measure":[27],"data":[28,58,65],"importance":[29,82,109],"via":[30,93],"e.g.":[31],"sample":[32],"hardness.":[33],"However,":[34],"when":[35],"misspecified,":[40],"deteriorate.":[44],"Since":[45,111],"misspecification":[47],"persistent":[49],"in":[50,89],"real":[51],"systems,":[53],"we":[54,71,117,130],"instead":[55],"propose":[56],"model-agnostic":[57,124],"by":[61,68,97],"only":[62],"exploring":[63],"input":[64],"structure":[66],"represented":[67],"graphs.":[69],"Specifically,":[70],"study":[72],"topology":[74],"user-item":[77,85,91],"graph":[78,94],"estimate":[80],"each":[84],"interaction":[86],"(an":[87],"edge":[88],"graph)":[92],"conductance,":[95],"followed":[96],"propagation":[99],"step":[100],"on":[101,142,148],"network":[103],"smooth":[105],"out":[106],"estimated":[108],"value.":[110],"our":[112,155],"proposed":[113,156],"method":[114,141],"model-agnostic,":[116],"can":[118],"marry":[119],"merits":[121],"both":[123],"methods.":[128],"Empirically,":[129],"show":[131],"that":[132,154],"combing":[133],"two":[135],"consistently":[136],"improves":[137],"over":[138],"any":[139],"single":[140],"datasets.":[145],"Experimental":[146],"results":[147,160],"KuaiRec":[149],"MIND":[151],"datasets":[152],"demonstrate":[153],"achieve":[158],"superior":[159],"compared":[161],"baseline":[163],"approaches.":[164]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}