{"id":"https://openalex.org/W4213384663","doi":"https://doi.org/10.1145/3488560.3498535","title":"Hierarchical Imitation Learning via Subgoal Representation Learning for Dynamic Treatment Recommendation","display_name":"Hierarchical Imitation Learning via Subgoal Representation Learning for Dynamic Treatment Recommendation","publication_year":2022,"publication_date":"2022-02-11","ids":{"openalex":"https://openalex.org/W4213384663","doi":"https://doi.org/10.1145/3488560.3498535"},"language":"en","primary_location":{"id":"doi:10.1145/3488560.3498535","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488560.3498535","pdf_url":null,"source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search 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 Fifteenth ACM International Conference on Web Search 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/A5083964854","display_name":"Lu Wang","orcid":"https://orcid.org/0000-0002-7305-1496"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Wang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054330014","display_name":"Ruiming Tang","orcid":"https://orcid.org/0000-0002-9224-2431"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiming Tang","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101434435","display_name":"Xiaofeng He","orcid":"https://orcid.org/0000-0002-6911-348X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng He","raw_affiliation_strings":["East China Normal University, Shanghai, China","Huawei Noah's Ark Lab, Shenzhen, Hong Kong"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, Hong Kong","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083350101","display_name":"Xiuqiang He","orcid":"https://orcid.org/0000-0002-4115-8205"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuqiang He","raw_affiliation_strings":["East China Normal University, Shanghai, China","Huawei Noah's Ark Lab, Shenzhen, Hong Kong"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, Hong Kong","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083964854"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":1.5566,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84577677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1081","last_page":"1089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9995999932289124,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9821000099182129,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9653000235557556,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.8729181289672852},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7371416687965393},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.648928165435791},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6394841074943542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5646358728408813},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5500659942626953},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5269173979759216},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2595495581626892},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12963172793388367},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08044743537902832}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.8729181289672852},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7371416687965393},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.648928165435791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6394841074943542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5646358728408813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5500659942626953},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5269173979759216},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2595495581626892},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12963172793388367},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08044743537902832},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3488560.3498535","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3488560.3498535","pdf_url":null,"source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search 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 Fifteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2121517924","https://openalex.org/W2190781736","https://openalex.org/W2963761387"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2665305151"],"abstract_inverted_index":{"Dynamic":[0],"Treatment":[1],"Recommendation":[2],"(DTR)":[3],"is":[4,38,80,153,169,195],"a":[5,52,73,124,134,139,165,215,236],"sequence":[6],"of":[7,162,232],"tailored":[8],"treatment":[9],"decision":[10],"rules":[11],"which":[12],"can":[13,64],"be":[14,66],"grouped":[15,67],"as":[16,36,114],"individual":[17,70],"sub-tasks.":[18],"As":[19,51],"the":[20,59,148,157,230],"reward":[21,49],"signals":[22],"in":[23,40,61],"DTR":[24],"are":[25,93],"hard":[26],"to":[27,68,82,98,105,155,171,184,197],"design,":[28],"Imitation":[29,111],"Learning":[30,112],"(IL)":[31],"has":[32],"achieved":[33],"great":[34],"success":[35],"it":[37],"effective":[39,174],"mimicking":[41],"doctors'":[42,62,84,209],"behaviors":[43,60,92],"from":[44,95,219],"their":[45],"demonstrations":[46,63,85],"without":[47,144],"explicit":[48],"signals.":[50],"patient":[53,233],"may":[54],"have":[55],"several":[56],"different":[57,189],"symptoms,":[58],"often":[65],"handle":[69],"symptoms.":[71],"However,":[72],"single":[74],"flat":[75],"policy":[76,136,150,201,204],"learned":[77,154],"by":[78,101,235],"IL":[79],"difficult":[81],"mimic":[83],"with":[86,225,243],"such":[87],"hierarchical":[88,244],"structure,":[89],"where":[90,133],"low-level":[91,149,203],"switching":[94],"one":[96],"symptom":[97],"another":[99],"controlled":[100],"high-level":[102,135,200],"decisions.":[103],"Due":[104],"this":[106,120],"observation,":[107],"we":[108,122,181,211],"consider":[109],"Hierarchical":[110],"methods":[113],"good":[115],"solutions":[116],"for":[117,131,141,151,176],"DTR.":[118],"In":[119],"paper,":[121],"propose":[123],"novel":[125],"Subgoal":[126],"conditioned":[127],"HIL":[128],"framework":[129],"(short":[130],"SHIL),":[132],"sequentially":[137],"sets":[138],"subgoal":[140],"each":[142,177],"sub-task":[143],"prior":[145,163],"knowledge,":[146,164],"and":[147,202,239],"sub-tasks":[152],"reach":[156],"subgoal.":[158,178],"To":[159,191],"get":[160],"rid":[161],"self-supervised":[166],"learning":[167],"method":[168],"proposed":[170],"learn":[172,198],"an":[173],"representation":[175],"More":[179],"specifically,":[180],"carefully":[182],"designed":[183],"encourage":[185],"diverse":[186],"representations":[187],"among":[188],"subgoals.":[190],"demonstrate":[192],"that":[193,205],"SHIL":[194,228],"able":[196],"meaningful":[199],"accurately":[206],"reproduces":[207],"complex":[208],"demonstrations,":[210],"conduct":[212],"experiments":[213],"on":[214],"real-world":[216],"medical":[217],"data":[218],"health":[220],"care":[221],"domain,":[222],"MIMIC-III.":[223],"Compared":[224],"state-of-the-art":[226],"baselines,":[227],"improves":[229],"likelihood":[231],"survival":[234],"significant":[237],"margin":[238],"provides":[240],"explainable":[241],"recommendation":[242],"structure.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}