{"id":"https://openalex.org/W4401863356","doi":"https://doi.org/10.1145/3637528.3671570","title":"A Self-boosted Framework for Calibrated Ranking","display_name":"A Self-boosted Framework for Calibrated Ranking","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863356","doi":"https://doi.org/10.1145/3637528.3671570"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671570","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5049123048","display_name":"Shunyu Zhang","orcid":"https://orcid.org/0009-0000-1936-1162"},"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":"Shunyu Zhang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-1936-1162","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680695","display_name":"Hu Liu","orcid":"https://orcid.org/0000-0003-2225-7387"},"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":"Hu Liu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2225-7387","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048260164","display_name":"Wentian Bao","orcid":"https://orcid.org/0009-0001-2195-0553"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentian Bao","raw_affiliation_strings":["Columbia University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2195-0553","affiliations":[{"raw_affiliation_string":"Columbia University, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054552826","display_name":"Enyun Yu","orcid":"https://orcid.org/0009-0009-0847-7464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enyun Yu","raw_affiliation_strings":["Northeasten University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0847-7464","affiliations":[{"raw_affiliation_string":"Northeasten University, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083873109","display_name":"Yang Song","orcid":"https://orcid.org/0000-0002-1714-5527"},"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":"Yang Song","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1714-5527","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":[],"apc_list":null,"apc_paid":null,"fwci":1.2792,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84933666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6226","last_page":"6235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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/T11106","display_name":"Data Management and Algorithms","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.6450567841529846},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5815284252166748},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3518804907798767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34288284182548523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6450567841529846},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5815284252166748},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3518804907798767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34288284182548523}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671570","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1976517433","https://openalex.org/W2030978506","https://openalex.org/W2040337753","https://openalex.org/W2061879449","https://openalex.org/W2062806705","https://openalex.org/W2069870183","https://openalex.org/W2091158010","https://openalex.org/W2108862644","https://openalex.org/W2115584760","https://openalex.org/W2158698691","https://openalex.org/W2475334473","https://openalex.org/W2548695521","https://openalex.org/W2607662938","https://openalex.org/W2723293840","https://openalex.org/W2770508375","https://openalex.org/W2902365885","https://openalex.org/W2959353218","https://openalex.org/W2964182926","https://openalex.org/W3001835520","https://openalex.org/W3036320503","https://openalex.org/W3093519337","https://openalex.org/W3093945404","https://openalex.org/W3098468692","https://openalex.org/W3102243698","https://openalex.org/W3105136066","https://openalex.org/W3132308722","https://openalex.org/W3153687269","https://openalex.org/W4212774754","https://openalex.org/W4290928026","https://openalex.org/W4306317487","https://openalex.org/W4385568035","https://openalex.org/W4387561071","https://openalex.org/W4387848868"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2118564381","https://openalex.org/W2163901716","https://openalex.org/W2152204162","https://openalex.org/W2739821120","https://openalex.org/W2150136235","https://openalex.org/W2026095310","https://openalex.org/W2140661912","https://openalex.org/W2056806613","https://openalex.org/W2153069032"],"abstract_inverted_index":{"Scale-calibrated":[0],"ranking":[1,12,24,34,80,120,187,217,222,277],"systems":[2],"are":[3,194,282],"ubiquitous":[4],"in":[5,21,162,214,336],"real-world":[6],"applications":[7],"nowadays,":[8],"which":[9,61,129,160,291],"pursue":[10],"accurate":[11],"quality":[13],"and":[14,35,78,138,168,255,276,285,306,320,334,342],"calibrated":[15,39,75],"probabilistic":[16,158],"predictions":[17,248],"simultaneously.":[18],"For":[19],"instance,":[20],"the":[22,26,41,63,109,119,141,149,171,185,190,209,215,221,228,234,243,246,258,273,287,294,328,343],"advertising":[23],"system,":[25],"predicted":[27,186],"click-through":[28],"rate":[29],"(CTR)":[30],"is":[31,237,269],"utilized":[32],"for":[33,40,58,135,179,230],"required":[36],"to":[37,89,107,117,253,260,271],"be":[38,225],"downstream":[42],"cost-per-click":[43],"ads":[44],"bidding.":[45],"Recently,":[46],"multi-objective":[47,94,146],"based":[48],"methods":[49,105,147],"have":[50],"been":[51,132,325],"wildly":[52],"adopted":[53],"as":[54],"a":[55,69,79,114,156,163,176,238,266],"standard":[56],"approach":[57],"Calibrated":[59,180],"Ranking,":[60],"incorporates":[62],"combination":[64],"of":[65,212,332,346],"two":[66,100,150,172,280],"loss":[67,71,81,153,223,275],"functions:":[68],"pointwise":[70],"that":[72,82,220,311],"focuses":[73],"on":[74,155,302,317,327,340,350],"absolute":[76],"values":[77],"emphasizes":[83],"relative":[84],"orderings.":[85],"However,":[86],"when":[87],"applied":[88,283],"industrial":[90,303],"online":[91,191,307],"applications,":[92],"existing":[93,145],"CR":[95],"approaches":[96],"still":[97],"suffer":[98],"from":[99],"crucial":[101],"limitations":[102],"First,":[103],"previous":[104],"need":[106,229],"aggregate":[108],"full":[110],"candidate":[111],"list":[112],"within":[113],"single":[115,157,205],"mini-batch":[116],"compute":[118],"loss.":[121,278],"Such":[122],"aggregation":[123],"strategy":[124],"violates":[125],"extensive":[126],"data":[127],"shuffling":[128],"has":[130,324],"long":[131],"proven":[133],"beneficial":[134],"preventing":[136],"overfitting,":[137],"thus":[139],"degrades":[140],"training":[142,244],"effectiveness.":[143],"Second,":[144],"apply":[148],"inherently":[151],"conflicting":[152],"functions":[154],"prediction,":[159],"results":[161,335],"sub-optimal":[164,295],"trade-off":[165,296],"between":[166],"calibration":[167,267,288,319],"ranking.To":[169],"tackle":[170],"limitations,":[173],"we":[174],"propose":[175],"Self-Boosted":[177],"framework":[178],"Ranking":[181],"(SBCR).":[182],"In":[183],"SBCR,":[184],"scores":[188,213],"by":[189],"deployed":[192,235,326],"model":[193,236,259],"dumped":[195,247],"into":[196],"context":[197,202],"features.":[198],"With":[199],"these":[200],"additional":[201],"features,":[203],"each":[204],"item":[206],"can":[207,224,313],"perceive":[208],"overall":[210],"distribution":[211],"whole":[216],"list,":[218],"so":[219],"constructed":[226],"without":[227],"sample":[231],"aggregation.":[232],"As":[233],"few":[239],"versions":[240],"older":[241],"than":[242],"model,":[245],"reveal":[249],"what":[250],"was":[251],"failed":[252],"learn":[254],"keep":[256],"boosting":[257],"correct":[261],"previously":[262],"mis-predicted":[263],"items.":[264],"Moreover,":[265],"module":[268,289],"introduced":[270],"decouple":[272],"point":[274],"The":[279],"losses":[281],"before":[284],"after":[286],"separately,":[290],"elegantly":[292],"addresses":[293],"problem.":[297],"We":[298],"conduct":[299],"comprehensive":[300],"experiments":[301],"scale":[304],"datasets":[305],"A/B":[308],"tests,":[309],"demonstrating":[310],"SBCR":[312],"achieve":[314],"advanced":[315],"performance":[316,338],"both":[318],"ranking.":[321],"Our":[322],"method":[323],"video":[329],"search":[330],"system":[331],"Kuaishou,":[333],"significant":[337],"improvements":[339],"CTR":[341],"total":[344],"amount":[345],"time":[347],"users":[348],"spend":[349],"Kuaishou.":[351]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}