{"id":"https://openalex.org/W2951920403","doi":"https://doi.org/10.1145/3292500.3330974","title":"Adaptive-Halting Policy Network for Early Classification","display_name":"Adaptive-Halting Policy Network for Early Classification","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2951920403","doi":"https://doi.org/10.1145/3292500.3330974","mag":"2951920403"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330974","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330974","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330974","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330974","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075881948","display_name":"Thomas Hartvigsen","orcid":"https://orcid.org/0000-0002-5288-2792"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas Hartvigsen","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032316925","display_name":"Cansu \u015een","orcid":"https://orcid.org/0000-0003-3355-2736"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cansu Sen","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002930471","display_name":"Xiangnan Kong","orcid":"https://orcid.org/0000-0002-7403-5869"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangnan Kong","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008269094","display_name":"Elke A. Rundensteiner","orcid":"https://orcid.org/0000-0001-5375-9254"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elke Rundensteiner","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075881948"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":3.0058,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.92131207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9998000264167786,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9772999882698059,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9745000004768372,"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/discriminator","display_name":"Discriminator","score":0.8155461549758911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7932896614074707},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7575611472129822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6942423582077026},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.671954870223999},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6475793123245239},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5353862047195435},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4879435896873474},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.46245551109313965},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4159081280231476},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23775911331176758}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8155461549758911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932896614074707},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7575611472129822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6942423582077026},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.671954870223999},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6475793123245239},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5353862047195435},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4879435896873474},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.46245551109313965},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4159081280231476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23775911331176758},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330974","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330974","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330974","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330974","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330974","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330974","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6600000262260437,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1526762741","display_name":null,"funder_award_id":"IIS-1718310","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2698097454","display_name":null,"funder_award_id":"15030","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4083504884","display_name":null,"funder_award_id":"IIS-1815866","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5170210233","display_name":null,"funder_award_id":"IIS-1815866,CNS-1852498,CNS-1560229,IIS-1718310","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5436171597","display_name":null,"funder_award_id":"1815866","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6066375537","display_name":null,"funder_award_id":"CNS-1560229","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6249850884","display_name":"REU SITE: DATA SCIENCE RESEARCH FOR HEALTHY COMMUNITIES IN THE DIGITAL AGE","funder_award_id":"1852498","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6527620295","display_name":"III: Small: Collaborative Research: Towards End-to-End Knowledge Discovery in Complex Brain Networks","funder_award_id":"1718310","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7339316398","display_name":"REU SITE: Data Science Research for Safe, Sustainable and Healthy Communities","funder_award_id":"1560229","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7786263690","display_name":null,"funder_award_id":"50306","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7935952682","display_name":null,"funder_award_id":"P200A150306","funder_id":"https://openalex.org/F4320309210","funder_display_name":"U.S. Department of Health, Education and Welfare"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309210","display_name":"U.S. Department of Health, Education and Welfare","ror":"https://ror.org/033jnv181"},{"id":"https://openalex.org/F4320317074","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951920403.pdf","grobid_xml":"https://content.openalex.org/works/W2951920403.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W600165676","https://openalex.org/W1509672901","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1646152356","https://openalex.org/W1699074795","https://openalex.org/W1810943226","https://openalex.org/W1973590682","https://openalex.org/W1978522669","https://openalex.org/W2002828701","https://openalex.org/W2009617787","https://openalex.org/W2029438113","https://openalex.org/W2041486528","https://openalex.org/W2053744708","https://openalex.org/W2064675550","https://openalex.org/W2074848383","https://openalex.org/W2078765398","https://openalex.org/W2107878631","https://openalex.org/W2110485445","https://openalex.org/W2119717200","https://openalex.org/W2125353221","https://openalex.org/W2140766383","https://openalex.org/W2141125852","https://openalex.org/W2143612262","https://openalex.org/W2147527908","https://openalex.org/W2155027007","https://openalex.org/W2242818861","https://openalex.org/W2342546612","https://openalex.org/W2396881363","https://openalex.org/W2403962807","https://openalex.org/W2472970127","https://openalex.org/W2765566334","https://openalex.org/W2767591115","https://openalex.org/W2902760701","https://openalex.org/W2950178297"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2057775761","https://openalex.org/W1608433645","https://openalex.org/W2964074194"],"abstract_inverted_index":{"Early":[0],"classification":[1,37,74],"of":[2,8,12,41,124,128,178],"time":[3,14,31,89],"series":[4,15,90],"is":[5,18,28,33],"the":[6,9,104,125,139,156],"prediction":[7],"class":[10],"label":[11],"a":[13,60,109,129,134,142,145,175],"before":[16],"it":[17,32],"observed":[19],"in":[20,39,193],"its":[21,161],"entirety.":[22],"In":[23],"time-sensitive":[24],"domains":[25],"where":[26],"information":[27],"collected":[29],"over":[30],"worth":[34],"sacrificing":[35],"some":[36],"accuracy":[38,54,194],"favor":[40],"earlier":[42],"predictions,":[43],"ideally":[44],"early":[45,73],"enough":[46],"for":[47],"actions":[48],"to":[49,66,87,96,168],"be":[50],"taken.":[51],"However,":[52],"since":[53],"and":[55,91,98,159,182,195],"earliness":[56,196],"are":[57],"contradictory":[58,114],"objectives,":[59],"solution":[61],"must":[62],"address":[63],"this":[64,80,100],"challenge":[65],"discover":[67],"task-dependent":[68],"trade-offs.":[69],"We":[70],"design":[71],"an":[72],"model,":[75],"called":[76],"EARLIEST,":[77],"which":[78,94],"tackles":[79],"multi-objective":[81],"optimization":[82],"problem,":[83],"jointly":[84],"learning":[85,103,141,147],"(1)":[86],"classify":[88],"(2)":[92],"at":[93],"timestep":[95],"halt":[97],"generate":[99],"prediction.":[101],"By":[102],"objectives":[105],"together,":[106],"we":[107,185],"achieve":[108],"user-controlled":[110],"balance":[111],"between":[112],"these":[113],"goals":[115],"while":[116,197],"capturing":[117],"their":[118],"natural":[119],"relationship.":[120],"Our":[121],"model":[122,158],"consists":[123],"novel":[126],"pairing":[127],"recurrent":[130,157],"discriminator":[131],"network":[132],"with":[133,138],"stochastic":[135],"policy":[136,151],"network,":[137],"latter":[140],"halting-policy":[143],"as":[144],"reinforcement":[146],"task.":[148],"The":[149],"learned":[150],"interprets":[152],"representations":[153],"generated":[154],"by":[155],"controls":[160],"dynamics,":[162],"sequentially":[163],"deciding":[164],"whether":[165],"or":[166],"not":[167],"request":[169],"observations":[170],"from":[171],"future":[172],"timesteps.":[173],"For":[174],"rich":[176],"variety":[177],"datasets":[179],"(four":[180],"synthetic":[181],"three":[183],"real-world),":[184],"demonstrate":[186],"that":[187],"EARLIEST":[188],"consistently":[189],"out-performs":[190],"state-of-the-art":[191],"alternatives":[192],"discovering":[198],"signal":[199],"locations":[200],"without":[201],"supervision.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}