{"id":"https://openalex.org/W4401330311","doi":"https://doi.org/10.1145/3664190.3672522","title":"On Adaptive Knowledge Distillation with Generalized KL-Divergence Loss for Ranking Model Refinement","display_name":"On Adaptive Knowledge Distillation with Generalized KL-Divergence Loss for Ranking Model Refinement","publication_year":2024,"publication_date":"2024-08-02","ids":{"openalex":"https://openalex.org/W4401330311","doi":"https://doi.org/10.1145/3664190.3672522"},"language":"en","primary_location":{"id":"doi:10.1145/3664190.3672522","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664190.3672522","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664190.3672522","source":null,"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 2024 ACM SIGIR International Conference on Theory of Information Retrieval","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/10.1145/3664190.3672522","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032384435","display_name":"Yingrui Yang","orcid":"https://orcid.org/0000-0001-6454-5796"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingrui Yang","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6454-5796","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037790148","display_name":"Shanxiu He","orcid":"https://orcid.org/0009-0008-8581-6733"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanxiu He","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0008-8581-6733","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060730782","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0003-1902-3387"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1902-3387","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9907000064849854,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9907000064849854,"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/T10320","display_name":"Neural Networks and Applications","score":0.9886999726295471,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.988099992275238,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.8330487608909607},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.8177968263626099},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7360920906066895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6975420713424683},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5671236515045166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5086432695388794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4984323978424072},{"id":"https://openalex.org/keywords/refining","display_name":"Refining (metallurgy)","score":0.42888781428337097},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15014922618865967},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13724437355995178}],"concepts":[{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.8330487608909607},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.8177968263626099},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7360920906066895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6975420713424683},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5671236515045166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5086432695388794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4984323978424072},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.42888781428337097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15014922618865967},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13724437355995178},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C147789679","wikidata":"https://www.wikidata.org/wiki/Q11372","display_name":"Physical chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664190.3672522","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664190.3672522","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664190.3672522","source":null,"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 2024 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664190.3672522","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664190.3672522","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664190.3672522","source":null,"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 2024 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401330311.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2115584760","https://openalex.org/W2884561390","https://openalex.org/W3157758108","https://openalex.org/W3201233724","https://openalex.org/W3206455169","https://openalex.org/W4206121183","https://openalex.org/W4283805006","https://openalex.org/W4284664419","https://openalex.org/W4384891026","https://openalex.org/W4385688710"],"related_works":["https://openalex.org/W1595345252","https://openalex.org/W2392526918","https://openalex.org/W2362540361","https://openalex.org/W2019560916","https://openalex.org/W2361983698","https://openalex.org/W2347697528","https://openalex.org/W2354123794","https://openalex.org/W2372508235","https://openalex.org/W2560036917","https://openalex.org/W2349506406"],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1,69],"is":[2,117],"useful":[3],"in":[4,26,49,57,66,70,108],"training":[5,38,94],"a":[6,13,20,44,50,93,98,103,126],"neural":[7],"document":[8],"ranking":[9,55],"model":[10,17,100,116],"by":[11],"employing":[12],"teacher":[14,21,34,78,115],"to":[15,72,101],"guide":[16],"refinement.":[18],"As":[19],"may":[22],"not":[23],"perform":[24],"well":[25],"all":[27],"cases,":[28],"over-calibration":[29],"between":[30],"the":[31,73,77,85,110,114,120,133],"student":[32,80,99,121],"and":[33,61,79,89,96,135],"models":[35,56],"can":[36],"make":[37],"less":[39],"effective.":[40],"This":[41,82,123],"paper":[42,124],"studies":[43],"generalized":[45,139],"KL":[46],"divergence":[47],"loss":[48,83],"weighted":[51],"form":[52],"for":[53,92],"refining":[54],"searching":[58],"text":[59],"documents,":[60],"examines":[62],"its":[63],"formal":[64],"properties":[65],"balancing":[67],"knowledge":[68],"adaption":[71],"relative":[74],"performance":[75],"of":[76,87,137],"models.":[81],"differentiates":[84],"role":[86],"positive":[88],"negative":[90],"documents":[91],"query,":[95],"allows":[97],"take":[102],"conservative":[104],"or":[105],"deviate":[106],"approach":[107],"imitating":[109],"teacher's":[111],"behavior":[112,134],"when":[113],"worse":[118],"than":[119],"model.":[122],"presents":[125],"detailed":[127],"theoretical":[128],"analysis":[129],"with":[130],"experiments":[131],"on":[132],"usefulness":[136],"this":[138],"loss.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}