{"id":"https://openalex.org/W4306317802","doi":"https://doi.org/10.1145/3511808.3557094","title":"Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks","display_name":"Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317802","doi":"https://doi.org/10.1145/3511808.3557094"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557094","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100443565","display_name":"Ze Wang","orcid":"https://orcid.org/0009-0004-6220-4938"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ze Wang","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036945708","display_name":"Guogang Liao","orcid":"https://orcid.org/0009-0002-6530-7102"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guogang Liao","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064189829","display_name":"Xiaowen Shi","orcid":"https://orcid.org/0000-0001-6532-4522"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowen Shi","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027645208","display_name":"Xiaoxu Wu","orcid":"https://orcid.org/0000-0003-0598-4697"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxu Wu","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080460228","display_name":"Chuheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuheng Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109602541","display_name":"Yongkang Wang","orcid":"https://orcid.org/0000-0003-0192-3539"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkang Wang","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673283","display_name":"Xingxing Wang","orcid":"https://orcid.org/0000-0003-4437-5229"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingxing Wang","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391568","display_name":"Dong Wang","orcid":"https://orcid.org/0009-0008-7738-1688"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Meituan, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100443565"],"corresponding_institution_ids":["https://openalex.org/I4210087373"],"apc_list":null,"apc_paid":null,"fwci":0.5821,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67807425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3555","last_page":"3564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9976000189781189,"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"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8859672546386719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8288077116012573},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6122709512710571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5916267037391663},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5602037906646729},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5045167207717896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48873162269592285},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4682190418243408},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44193947315216064},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4386710524559021},{"id":"https://openalex.org/keywords/revenue","display_name":"Revenue","score":0.4152989685535431}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8859672546386719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288077116012573},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6122709512710571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916267037391663},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5602037906646729},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5045167207717896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48873162269592285},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4682190418243408},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44193947315216064},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4386710524559021},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.4152989685535431},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557094","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W102349725","https://openalex.org/W2145339207","https://openalex.org/W2467077639","https://openalex.org/W2723293840","https://openalex.org/W2769112066","https://openalex.org/W2797234205","https://openalex.org/W2799173935","https://openalex.org/W2808227867","https://openalex.org/W2891076394","https://openalex.org/W2963634205","https://openalex.org/W2990138404","https://openalex.org/W3007094061","https://openalex.org/W3043381552","https://openalex.org/W3080386552","https://openalex.org/W3094280243","https://openalex.org/W3094577760","https://openalex.org/W3103141630","https://openalex.org/W3157410348","https://openalex.org/W3173331009","https://openalex.org/W3196402383","https://openalex.org/W4205423437","https://openalex.org/W4247154108"],"related_works":["https://openalex.org/W2101355568","https://openalex.org/W4319083788","https://openalex.org/W3049166411","https://openalex.org/W4287688416","https://openalex.org/W3090436287","https://openalex.org/W2764311431","https://openalex.org/W4297789760","https://openalex.org/W4287647350","https://openalex.org/W56580342","https://openalex.org/W2492384539"],"abstract_inverted_index":{"With":[0],"the":[1,32,75,146,149,161,174,178],"recent":[2,35],"prevalence":[3],"of":[4,34,58,77,148],"reinforcement":[5],"learning":[6,125],"(RL),":[7],"there":[8],"have":[9],"been":[10],"tremendous":[11],"interests":[12],"in":[13,19,54],"utilizing":[14],"RL":[15,78],"for":[16,95,173],"ads":[17,37,96,133],"allocation":[18,38,97],"recommendation":[20],"platforms":[21],"(e.g.,":[22],"e-commerce":[23],"and":[24,80,123,155,169],"news":[25],"feed":[26],"sites).":[27],"To":[28,85],"achieve":[29,170],"better":[30,100,166],"allocation,":[31],"input":[33],"RL-based":[36,93],"methods":[39],"is":[40],"upgraded":[41],"from":[42],"point-wise":[43],"single":[44],"item":[45,48],"to":[46,64,128,144,177],"list-wise":[47,66,101,167],"arrangement.":[49],"However,":[50],"this":[51,87],"also":[52],"results":[53,158],"a":[55,91],"high-dimensional":[56],"space":[57],"state-action":[59],"pairs,":[60],"making":[61],"it":[62],"difficult":[63],"learn":[65,165],"representations":[67,102,168],"with":[68],"good":[69],"generalization":[70],"ability.":[71],"This":[72],"further":[73],"hinders":[74],"exploration":[76],"agents":[79],"causes":[81],"poor":[82],"sample":[83],"efficiency.":[84],"address":[86],"problem,":[88],"we":[89,113],"propose":[90,114],"novel":[92],"approach":[94],"which":[98],"learns":[99],"by":[103],"leveraging":[104],"task-specific":[105],"signals":[106],"on":[107,120,132,139],"Meituan":[108,140],"food":[109,141],"delivery":[110,142],"platform.":[111],"Specifically,":[112],"three":[115],"different":[116],"auxiliary":[117,151],"tasks":[118],"based":[119],"reconstruction,":[121],"prediction,":[122],"contrastive":[124],"respectively":[126],"according":[127],"prior":[129],"domain":[130],"knowledge":[131],"allocation.":[134],"We":[135],"conduct":[136],"extensive":[137],"experiments":[138],"platform":[143,175],"evaluate":[145],"effectiveness":[147],"proposed":[150,162],"tasks.":[152],"Both":[153],"offline":[154],"online":[156],"experimental":[157],"show":[159],"that":[160],"method":[163],"can":[164],"higher":[171],"revenue":[172],"compared":[176],"state-of-the-art":[179],"baselines.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}