{"id":"https://openalex.org/W4282914877","doi":"https://doi.org/10.1145/3534678.3539264","title":"Balancing Bias and Variance for Active Weakly Supervised Learning","display_name":"Balancing Bias and Variance for Active Weakly Supervised Learning","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4282914877","doi":"https://doi.org/10.1145/3534678.3539264"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539264","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539264","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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 28th 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/A5053521358","display_name":"Hitesh Sapkota","orcid":"https://orcid.org/0000-0002-5717-8753"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hitesh Sapkota","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081837918","display_name":"Qi Yu","orcid":"https://orcid.org/0000-0002-0426-5407"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Yu","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, NY, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":0.0924,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32838263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1536","last_page":"1546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9993000030517578,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9916999936103821,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9736999869346619,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.7143784761428833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7043818235397339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6256766319274902},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5817670226097107},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46966540813446045},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4667525589466095},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.45096614956855774},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.43092572689056396},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37354370951652527},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34360840916633606},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25008058547973633},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1929728090763092}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7143784761428833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7043818235397339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6256766319274902},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5817670226097107},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46966540813446045},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4667525589466095},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.45096614956855774},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.43092572689056396},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37354370951652527},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34360840916633606},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25008058547973633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1929728090763092},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539264","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539264","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4524045949","display_name":"CHS:Small:Utilizing synergy between human and computer information processing for complex visual information organization and use","funder_award_id":"1814450","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4981330806","display_name":null,"funder_award_id":"N00014-18-1-2875","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1560331282","https://openalex.org/W2027001671","https://openalex.org/W2037227137","https://openalex.org/W2110119381","https://openalex.org/W2113151258","https://openalex.org/W2128678390","https://openalex.org/W2133288557","https://openalex.org/W2471138382","https://openalex.org/W2531031089","https://openalex.org/W2560886373","https://openalex.org/W2747170135","https://openalex.org/W2922131323","https://openalex.org/W2963795951","https://openalex.org/W3118608800","https://openalex.org/W4295352925","https://openalex.org/W4301045096","https://openalex.org/W6679227803"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W4281727072","https://openalex.org/W2560201613","https://openalex.org/W2742914308","https://openalex.org/W2900543860","https://openalex.org/W2330004501","https://openalex.org/W2017089693","https://openalex.org/W3171633752","https://openalex.org/W2703295919","https://openalex.org/W2266833899"],"abstract_inverted_index":{"As":[0],"a":[1,46,106,121,131,164,179,188],"widely":[2],"used":[3],"weakly":[4],"supervised":[5],"learning":[6,11,43],"scheme,":[7],"modern":[8],"multiple":[9,41,234],"instance":[10,42,85,193],"(MIL)":[12],"models":[13],"achieve":[14],"competitive":[15],"performance":[16],"at":[17],"the":[18,58,71,82,97,125,147,198,204,208,213,228,239,245],"bag":[19,109,118,157,176,200],"level.":[20],"However,":[21],"instance-level":[22,59,76,229,241],"prediction,":[23],"which":[24,225],"is":[25,66,102,184],"essential":[26],"for":[27,52,223],"many":[28],"important":[29],"applications,":[30],"remains":[31],"largely":[32],"unsatisfactory.":[33],"We":[34],"propose":[35],"to":[36,55,68,79,145,151,167],"conduct":[37],"novel":[38,180],"active":[39,153],"deep":[40,165,169],"that":[44,101,186],"samples":[45],"small":[47],"subset":[48],"of":[49,75,94,124,174],"informative":[50],"instances":[51,150,222],"annotation,":[53,224],"aiming":[54,78],"significantly":[56,226],"boost":[57],"prediction.":[60,230],"A":[61],"variance":[62,74,98,126],"regularized":[63,99],"loss":[64,100,129],"function":[65,183,210],"designed":[67],"properly":[69],"balance":[70],"bias":[72,139],"and":[73,89,140,191,217],"predictions,":[77],"effectively":[80,218],"accommodate":[81],"highly":[83],"imbalanced":[84],"distribution":[86],"in":[87],"MIL":[88,128,206],"other":[90],"fundamental":[91],"challenges.":[92],"Instead":[93],"directly":[95],"minimizing":[96],"non-convex,":[103],"we":[104],"optimize":[105],"distributionally":[107],"robust":[108,117,156,199],"level":[110],"likelihood":[111,119,158],"as":[112],"its":[113],"convex":[114],"surrogate.":[115],"The":[116,155],"provides":[120],"good":[122],"approximation":[123],"based":[127],"with":[130,163],"strong":[132],"theoretical":[133],"guarantee.":[134],"It":[135],"also":[136],"automatically":[137],"balances":[138],"variance,":[141],"making":[142],"it":[143],"effective":[144],"identify":[146],"potentially":[148],"positive":[149,221],"support":[152,168],"sampling.":[154],"can":[159,211],"be":[160],"naturally":[161],"integrated":[162],"architecture":[166],"model":[170],"training":[171],"using":[172],"mini-batches":[173],"positive-negative":[175],"pairs.":[177],"Finally,":[178],"P-F":[181],"sampling":[182,209],"developed":[185],"combines":[187],"probability":[189],"vector":[190],"predicted":[192],"scores,":[194],"obtained":[195],"by":[196,244],"optimizing":[197],"likelihood.":[201],"By":[202],"leveraging":[203],"key":[205],"assumption,":[207],"explore":[212],"most":[214],"challenging":[215],"bags":[216],"detect":[219],"their":[220],"improves":[227],"Experiments":[231],"conducted":[232],"over":[233],"real-world":[235],"datasets":[236],"clearly":[237],"demonstrate":[238],"state-of-the-art":[240],"prediction":[242],"achieved":[243],"proposed":[246],"model.":[247]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}