{"id":"https://openalex.org/W4412876962","doi":"https://doi.org/10.1145/3711896.3737264","title":"Supervised Learning-enhanced Multi-Group Actor Critic for Live Stream Allocation in Feed","display_name":"Supervised Learning-enhanced Multi-Group Actor Critic for Live Stream Allocation in Feed","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876962","doi":"https://doi.org/10.1145/3711896.3737264"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737264","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737264","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737264","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737264","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027167942","display_name":"Jingxin Liu","orcid":"https://orcid.org/0000-0003-2526-8196"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxin Liu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2526-8196","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiang Gao","orcid":"https://orcid.org/0009-0005-4782-7261"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Gao","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-4782-7261","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083893412","display_name":"Yisha Li","orcid":"https://orcid.org/0000-0001-5280-5773"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YiSha Li","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5280-5773","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Li","orcid":"https://orcid.org/0009-0001-0536-540X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-0536-540X","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100568510","display_name":"Haiyang Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Lu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-7201-7635","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103053654","display_name":"Ben Wang","orcid":"https://orcid.org/0009-0007-1329-3876"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ben Wang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-1329-3876","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1402995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4611","last_page":"4622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9950000047683716,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.623304545879364},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.4904431998729706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4061208963394165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.623304545879364},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.4904431998729706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4061208963394165},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737264","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737264","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737264","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737264","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737264","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737264","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412876962.pdf","grobid_xml":"https://content.openalex.org/works/W4412876962.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2108682071","https://openalex.org/W2145339207","https://openalex.org/W2171033594","https://openalex.org/W2723293840","https://openalex.org/W2746553466","https://openalex.org/W2963842088","https://openalex.org/W2990138404","https://openalex.org/W3034853385","https://openalex.org/W3089160862","https://openalex.org/W3123348991","https://openalex.org/W3141797743","https://openalex.org/W3198517287","https://openalex.org/W3208324826","https://openalex.org/W4206497039","https://openalex.org/W4290827187","https://openalex.org/W4317837964","https://openalex.org/W4319792126","https://openalex.org/W4367310822","https://openalex.org/W4385567603","https://openalex.org/W4393153259"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"the":[1,13,29,41,114,198,214],"context":[2],"of":[3,45],"a":[4,124,136,162,184],"short":[5],"video":[6,30],"&":[7],"live":[8,14,26,46,73,192],"stream":[9,15,27,47,74,193],"mixed":[10],"recommendation":[11,16,85,110,232],"scenario,":[12],"system":[17],"(RS)":[18],"decides":[19],"whether":[20],"to":[21,28,66,87,173,188],"allocate":[22],"at":[23],"most":[24],"one":[25],"feed":[31],"for":[32,71,167],"each":[33],"user":[34,56,61,90],"request.":[35],"The":[36],"inappropriate":[37],"policy":[38,70,203],"which":[39,102],"ignores":[40],"long-term":[42,60,89],"negative":[43],"impact":[44],"allocation":[48],"can":[49],"significantly":[50],"affect":[51],"app":[52],"usage":[53],"duration":[54],"and":[55,99,105,170,177,206],"retention.":[57],"To":[58,118],"maximize":[59],"engagement,":[62],"it":[63],"is":[64],"crucial":[65],"determine":[67],"an":[68],"optimal":[69],"accurate":[72],"allocation.":[75,194],"Recently,":[76],"reinforcement":[77],"learning":[78,150],"(RL)":[79],"has":[80],"been":[81],"widely":[82],"applied":[83],"in":[84,107,113,230],"systems":[86],"capture":[88],"engagement.":[91],"However,":[92],"traditional":[93],"RL":[94],"algorithms":[95],"often":[96],"face":[97],"divergence":[98],"instability":[100],"problems,":[101],"restricts":[103],"application":[104],"deployment":[106],"large-scale":[108],"industrial":[109],"systems,":[111],"especially":[112],"aforementioned":[115],"challenging":[116],"scenario.":[117],"address":[119],"these":[120],"challenges,":[121],"we":[122,134,160,196],"propose":[123,183],"novel":[125,185],"Supervised":[126],"Learning-enhanced":[127],"Multi-Group":[128],"Actor":[129],"Critic":[130],"algorithm":[131,200],"(SL-MGAC).":[132],"Specifically,":[133],"introduce":[135],"supervised":[137,148],"learning-enhanced":[138],"actor-critic":[139],"framework":[140],"that":[141,213],"incorporates":[142],"variance":[143,176],"reduction":[144],"techniques,":[145],"where":[146],"multi-task":[147],"reward":[149,186],"helps":[151],"restrict":[152],"bootstrapping":[153],"error":[154],"accumulation":[155],"during":[156],"critic":[157,171],"learning.":[158],"Additionally,":[159],"design":[161],"multi-group":[163],"state":[164],"decomposition":[165],"module":[166],"both":[168],"actor":[169],"networks":[172],"reduce":[174],"prediction":[175],"improve":[178],"model":[179],"stability.":[180],"We":[181],"also":[182,226],"function":[187],"prevent":[189],"overly":[190],"greedy":[191],"Empirically,":[195],"evaluate":[197],"SL-MGAC":[199],"using":[201],"offline":[202],"evaluation":[204],"(OPE)":[205],"online":[207,231],"A/B":[208],"testing.":[209],"Experimental":[210],"results":[211],"demonstrate":[212],"proposed":[215],"method":[216],"not":[217],"only":[218],"outperforms":[219],"baseline":[220],"methods":[221],"under":[222],"platform-level":[223],"constraints,":[224],"but":[225],"exhibits":[227],"improved":[228],"stability":[229],"scenarios.":[233]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}