{"id":"https://openalex.org/W4401863644","doi":"https://doi.org/10.1145/3637528.3671762","title":"Model-Agnostic Random Weighting for Out-of-Distribution Generalization","display_name":"Model-Agnostic Random Weighting for Out-of-Distribution Generalization","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863644","doi":"https://doi.org/10.1145/3637528.3671762"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671762","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":"conference-paper","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/A5100897474","display_name":"Yue He","orcid":"https://orcid.org/0009-0009-1536-1179"},"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":"Yue He","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1536-1179","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101000993","display_name":"Pengfei Tian","orcid":"https://orcid.org/0009-0005-1747-0687"},"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":"Pengfei Tian","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-1747-0687","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061888153","display_name":"Renzhe Xu","orcid":"https://orcid.org/0000-0001-8418-0034"},"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":"Renzhe Xu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8418-0034","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072402741","display_name":"Xinwei Shen","orcid":"https://orcid.org/0000-0002-7801-4803"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Xinwei Shen","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7801-4803","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054379354","display_name":"Xingxuan Zhang","orcid":"https://orcid.org/0009-0002-4788-1127"},"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":"Xingxuan Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4788-1127","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009228005","display_name":"Peng Cui","orcid":"https://orcid.org/0000-0003-2957-8511"},"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":"Peng Cui","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2957-8511","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1050","last_page":"1061"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9872000217437744,"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"}},"topics":[{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9872000217437744,"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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9584000110626221,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9573000073432922,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7446541786193848},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7323096394538879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6350979804992676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3563237190246582},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33701300621032715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29481837153434753}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7446541786193848},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7323096394538879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6350979804992676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3563237190246582},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33701300621032715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29481837153434753},{"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671762","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":[{"display_name":"Reduced inequalities","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W1920962657","https://openalex.org/W2034368206","https://openalex.org/W2122838776","https://openalex.org/W2167366427","https://openalex.org/W2194775991","https://openalex.org/W2531031089","https://openalex.org/W2763549966","https://openalex.org/W2790376986","https://openalex.org/W2920807444","https://openalex.org/W2958360136","https://openalex.org/W2963043696","https://openalex.org/W2963351448","https://openalex.org/W2964288524","https://openalex.org/W2965237851","https://openalex.org/W3098528040","https://openalex.org/W4200617102","https://openalex.org/W4212774754","https://openalex.org/W4221168018","https://openalex.org/W4295352925","https://openalex.org/W4297969478","https://openalex.org/W6637618735"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2108418243","https://openalex.org/W2127804977","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213"],"abstract_inverted_index":{"Despite":[0],"the":[1,12,22,52,69,112,116,122,126,133,154,164],"encouraging":[2],"successes":[3],"in":[4,83,142,167],"numerous":[5],"applications,":[6],"machine":[7,168],"learning":[8,169],"methods":[9],"grounded":[10],"on":[11,38,59,89,149],"i.i.d.":[13],"assumption":[14],"often":[15],"experience":[16],"performance":[17,136],"deterioration":[18],"when":[19,140],"confronted":[20],"with":[21],"distribution":[23,119,165],"shift":[24],"between":[25],"training":[26,57,98,118],"and":[27,45],"test":[28,127,144],"data.":[29],"This":[30,129],"challenge":[31],"has":[32],"instigated":[33],"recent":[34],"research":[35],"endeavors":[36],"focusing":[37],"out-of-distribution":[39],"(OOD)":[40],"generalization.":[41],"A":[42],"particularly":[43],"pervasive":[44],"intricate":[46],"OOD":[47,81],"problem":[48],"is":[49],"to":[50,68,162],"enhance":[51],"model's":[53],"generalization":[54],"ability":[55],"by":[56],"it":[58],"samples":[60],"drawn":[61],"from":[62],"a":[63,73,79,102],"single":[64],"environment.":[65],"In":[66],"response":[67],"problem,":[70],"we":[71,108],"propose":[72],"simple":[74],"model-agnostic":[75],"method":[76,139],"tailored":[77],"for":[78],"practical":[80],"scenario":[82],"this":[84],"paper.":[85],"Our":[86],"approach":[87],"centers":[88],"pursuing":[90],"robust":[91],"weighted":[92],"empirical":[93],"risks,":[94],"utilizing":[95],"randomly":[96],"shifted":[97,117],"distributions":[99],"derived":[100],"through":[101],"specific":[103],"sample-based":[104],"weighting":[105],"strategy.":[106],"Furthermore,":[107],"theoretically":[109],"establish":[110],"that":[111],"expected":[113,123],"risk":[114,124],"of":[115,125,137,156],"can":[120],"bound":[121],"distribution.":[128],"theoretical":[130],"foundation":[131],"ensures":[132],"improved":[134],"prediction":[135],"our":[138,157],"employed":[141],"uncertain":[143],"distributions.":[145],"Extensive":[146],"experiments":[147],"conducted":[148],"diverse":[150],"real-world":[151],"datasets":[152],"affirm":[153],"effectiveness":[155],"method,":[158],"highlighting":[159],"its":[160],"potential":[161],"address":[163],"shifts":[166],"applications.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}