{"id":"https://openalex.org/W4306317920","doi":"https://doi.org/10.1145/3511808.3557139","title":"SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance","display_name":"SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317920","doi":"https://doi.org/10.1145/3511808.3557139"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557139","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/A5047883479","display_name":"Li Lyna Zhang","orcid":"https://orcid.org/0000-0003-0779-8310"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Lyna Zhang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109987","display_name":"Youkow Homma","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youkow Homma","raw_affiliation_strings":["Microsoft, Redmond, WA, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776575","display_name":"Yujing Wang","orcid":"https://orcid.org/0000-0002-6334-245X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Wang","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340964","display_name":"Min Wu","orcid":"https://orcid.org/0000-0003-0977-3600"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Wu","raw_affiliation_strings":["Microsoft, Redmond, WA, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438310","display_name":"Mao Yang","orcid":"https://orcid.org/0009-0009-6455-3898"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao Yang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046102901","display_name":"Ruofei Zhang","orcid":"https://orcid.org/0000-0002-4063-0109"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruofei Zhang","raw_affiliation_strings":["Microsoft, Redmond, WA, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534161","display_name":"Ting Cao","orcid":"https://orcid.org/0000-0002-9107-013X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Cao","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101956272","display_name":"Wei Shen","orcid":"https://orcid.org/0000-0003-3479-1165"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Shen","raw_affiliation_strings":["Microsoft, Redmond, WA, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5047883479"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.2081,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42169908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3654","last_page":"3663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.993399977684021,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.993399977684021,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9932000041007996,"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":0.9901000261306763,"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/inference","display_name":"Inference","score":0.7987970113754272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7782570123672485},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6412541270256042},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5832494497299194},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5467889308929443},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5209792256355286},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5006446838378906},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45993828773498535},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42448142170906067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41889142990112305},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3548986613750458},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17702797055244446},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1181829571723938},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07202470302581787}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7987970113754272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782570123672485},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6412541270256042},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5832494497299194},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5467889308929443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5209792256355286},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5006446838378906},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45993828773498535},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42448142170906067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41889142990112305},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3548986613750458},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17702797055244446},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1181829571723938},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07202470302581787},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557139","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":13,"referenced_works":["https://openalex.org/W2886851211","https://openalex.org/W2911964244","https://openalex.org/W2946794439","https://openalex.org/W2953171463","https://openalex.org/W2955051405","https://openalex.org/W2965658867","https://openalex.org/W3105966348","https://openalex.org/W3110978130","https://openalex.org/W3154851733","https://openalex.org/W3166731436","https://openalex.org/W3167266074","https://openalex.org/W3168622113","https://openalex.org/W4230563027"],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2355171581","https://openalex.org/W4229439743"],"abstract_inverted_index":{"Ad":[0],"relevance":[1,45,71],"modeling":[2],"plays":[3],"a":[4,55,73,90],"critical":[5],"role":[6],"in":[7,20,43],"online":[8,65],"advertising":[9],"systems":[10],"including":[11],"Microsoft":[12],"Bing.":[13],"To":[14],"leverage":[15],"powerful":[16],"transformers":[17],"like":[18],"BERT":[19,58],"this":[21],"low-latency":[22,57],"setting,":[23],"many":[24],"existing":[25],"approaches":[26,34],"perform":[27],"ad-side":[28],"computations":[29],"offline.":[30],"While":[31],"efficient,":[32],"these":[33],"are":[35],"unable":[36],"to":[37,53,62,89],"serve":[38],"cold":[39,68],"start":[40,69],"ads,":[41],"resulting":[42],"poor":[44],"predictions":[46],"for":[47,67],"such":[48],"ads.":[49],"This":[50],"work":[51],"aims":[52],"design":[54],"new,":[56],"via":[59],"structured":[60],"pruning":[61],"empower":[63],"real-time":[64],"inference":[66,101],"ads":[70],"on":[72],"CPU":[74],"platform.":[75],"Our":[76],"challenge":[77],"is":[78],"that":[79],"previous":[80],"methods":[81],"typically":[82],"prune":[83],"all":[84],"layers":[85],"of":[86],"the":[87],"transformer":[88],"high,":[91],"uniform":[92],"sparsity,":[93],"thereby":[94],"producing":[95],"models":[96],"which":[97],"cannot":[98],"achieve":[99],"satisfactory":[100],"speed":[102],"with":[103],"an":[104],"acceptable":[105],"accuracy.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}