{"id":"https://openalex.org/W7196933192","doi":"https://doi.org/10.1145/3770855.3818475","title":"SaFRO: Satisfaction-Aware Fusion via Dual-Relative Policy Optimization for Short-Video Search","display_name":"SaFRO: Satisfaction-Aware Fusion via Dual-Relative Policy Optimization for Short-Video Search","publication_year":2026,"publication_date":"2026-08-06","ids":{"openalex":"https://openalex.org/W7196933192","doi":"https://doi.org/10.1145/3770855.3818475"},"language":"en","primary_location":{"id":"doi:10.1145/3770855.3818475","doi":"https://doi.org/10.1145/3770855.3818475","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770855.3818475","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3770855.3818475","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5145558342","display_name":"Renzhe Zhou","orcid":"https://orcid.org/0009-0004-5453-0557","observed_orcids":["https://orcid.org/0009-0004-5453-0557"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renzhe Zhou","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0004-5453-0557","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071694471","display_name":"Songyang Li","orcid":"https://orcid.org/0009-0008-3507-8007","observed_orcids":["https://orcid.org/0009-0008-3507-8007"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songyang Li","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3507-8007","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144646721","display_name":"Feiran Zhu","orcid":"https://orcid.org/0009-0008-6198-2390","observed_orcids":["https://orcid.org/0009-0008-6198-2390"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiran Zhu","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0008-6198-2390","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109612967","display_name":"Chenglei Dai","orcid":"https://orcid.org/0009-0005-6252-3944","observed_orcids":["https://orcid.org/0009-0005-6252-3944"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglei Dai","raw_affiliation_strings":["Kuaishou Technology, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0005-6252-3944","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133724282","display_name":"Yi Zhang","orcid":"https://orcid.org/0009-0009-0975-6369","observed_orcids":["https://orcid.org/0009-0009-0975-6369"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0975-6369","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5145912395","display_name":"Yi Wang","orcid":"https://orcid.org/0009-0008-6816-9888","observed_orcids":["https://orcid.org/0009-0008-6816-9888"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6816-9888","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026923345","display_name":"Jingwei Zhuo","orcid":"https://orcid.org/0000-0001-8135-1061","observed_orcids":["https://orcid.org/0000-0001-8135-1061"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingwei Zhuo","raw_affiliation_strings":["Unaffiliated, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8135-1061","affiliations":[{"raw_affiliation_string":"Unaffiliated, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8654,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91781195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8585","last_page":"8594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9092000126838684,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9092000126838684,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.08950000256299973,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":9.999999747378752e-05,"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/user-retention","display_name":"user retention","score":0.7289999723434448},{"id":"https://openalex.org/keywords/kuaishou","display_name":"Kuaishou","score":0.8489999771118164}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7419000267982483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718999981880188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5429999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846000075340271},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.30079999566078186},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.26080000400543213}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3770855.3818475","doi":"https://doi.org/10.1145/3770855.3818475","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770855.3818475","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.19585","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.19585","pdf_url":"https://arxiv.org/pdf/2603.19585","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2603.19585","doi":"https://doi.org/10.48550/arxiv.2603.19585","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19585","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,"listed_in":[],"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"}],"best_oa_location":{"id":"doi:10.1145/3770855.3818475","doi":"https://doi.org/10.1145/3770855.3818475","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770855.3818475","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7196933192.pdf","grobid_xml":"https://content.openalex.org/works/W7196933192.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2173248099","https://openalex.org/W2339391301","https://openalex.org/W2736601468","https://openalex.org/W2809290718","https://openalex.org/W2945488061","https://openalex.org/W2958981444","https://openalex.org/W2964182926","https://openalex.org/W3087931390","https://openalex.org/W3132820540","https://openalex.org/W4290827187","https://openalex.org/W4300978609","https://openalex.org/W4324312897","https://openalex.org/W4367310822","https://openalex.org/W4385567603","https://openalex.org/W4386730581","https://openalex.org/W4391376794","https://openalex.org/W4391631327","https://openalex.org/W4393153259","https://openalex.org/W4393159871","https://openalex.org/W4394007749","https://openalex.org/W4399554003","https://openalex.org/W4400525872","https://openalex.org/W4409049124","https://openalex.org/W4409657268","https://openalex.org/W6891997250","https://openalex.org/W6929370958","https://openalex.org/W7120177137","https://openalex.org/W7196953391"],"related_works":["https://openalex.org/W7141607846","https://openalex.org/W7168369009","https://openalex.org/W4403707145","https://openalex.org/W7169868547","https://openalex.org/W4403220579","https://openalex.org/W4300801092","https://openalex.org/W7138961863","https://openalex.org/W4404837305","https://openalex.org/W7214361884","https://openalex.org/W4290827187"],"abstract_inverted_index":{"Multi-Task":[0],"Fusion":[1,140],"plays":[2],"a":[3,17,44,78,92,138],"pivotal":[4],"role":[5],"in":[6,86,177],"industrial":[7],"short-video":[8,87,164],"search":[9,55,165],"systems":[10],"by":[11],"aggregating":[12],"heterogeneous":[13],"prediction":[14],"signals":[15],"into":[16],"unified":[18],"ranking":[19,180],"score.":[20],"However,":[21],"existing":[22],"approaches":[23],"predominantly":[24],"optimize":[25,83],"for":[26,47],"immediate":[27],"engagement":[28],"metrics,":[29],"which":[30],"often":[31],"fail":[32],"to":[33,54,60,69,82,101,142],"align":[34],"with":[35],"long-term":[36,183],"user":[37,48,84,104,184],"satisfaction.":[38],"While":[39],"Reinforcement":[40],"Learning":[41],"(RL)":[42],"offers":[43],"promising":[45],"avenue":[46],"satisfaction":[49,85,105],"optimization,":[50],"its":[51],"direct":[52],"application":[53],"scenarios":[56],"is":[57],"non-trivial":[58],"due":[59],"the":[61,123,145],"inherent":[62],"data":[63],"sparsity":[64],"and":[65,132,157,182],"intent":[66],"constraints":[67],"compared":[68],"recommendation":[70],"feeds.":[71],"To":[72],"this":[73],"end,":[74],"we":[75,110,136],"propose":[76],"SaFRO,":[77],"novel":[79],"framework":[80],"designed":[81],"search.":[88],"We":[89],"first":[90],"construct":[91],"satisfaction-aware":[93],"reward":[94],"model":[95,144],"that":[96,121,168],"utilizes":[97],"query-level":[98],"behavioral":[99],"proxies":[100],"capture":[102],"holistic":[103],"beyond":[106],"item-level":[107],"interactions.":[108],"Then":[109],"introduce":[111],"Dual-Relative":[112],"Policy":[113],"Optimization":[114],"(DRPO),":[115],"an":[116],"efficient":[117],"policy":[118,125],"learning":[119],"method":[120],"updates":[122],"fusion":[124],"through":[126],"relative":[127],"preference":[128],"comparisons":[129],"within":[130],"groups":[131],"across":[133],"batches.":[134],"Furthermore,":[135],"design":[137],"Task-Relation-Aware":[139],"module":[141],"explicitly":[143],"interdependencies":[146],"among":[147],"different":[148],"objectives,":[149],"enabling":[150],"context-sensitive":[151],"weight":[152],"adaptation.":[153],"Extensive":[154],"offline":[155],"evaluations":[156],"large-scale":[158],"online":[159],"A/B":[160],"tests":[161],"on":[162],"Kuaishou":[163],"platform":[166],"demonstrate":[167],"SaFRO":[169],"significantly":[170],"outperforms":[171],"state-of-the-art":[172],"baselines,":[173],"delivering":[174],"substantial":[175],"gains":[176],"both":[178],"short-term":[179],"quality":[181],"retention.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-07T00:00:00"}