{"id":"https://openalex.org/W4412394942","doi":"https://doi.org/10.1145/3726302.3729992","title":"HCDS: Hierarchical Clustering for Cold-Start Few-Shot Data Selection","display_name":"HCDS: Hierarchical Clustering for Cold-Start Few-Shot Data Selection","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412394942","doi":"https://doi.org/10.1145/3726302.3729992"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3729992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729992","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729992","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in 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/10.1145/3726302.3729992","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032132303","display_name":"Yuhua Zhao","orcid":"https://orcid.org/0009-0001-5160-2859"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhua Zhao","raw_affiliation_strings":["College of Software, Nankai University, TianJin, China and Tianjin Key Laboratory of Software Experience and Human Computer Interaction, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0001-5160-2859","affiliations":[{"raw_affiliation_string":"College of Software, Nankai University, TianJin, China and Tianjin Key Laboratory of Software Experience and Human Computer Interaction, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112182924","display_name":"Zijian Han","orcid":"https://orcid.org/0009-0003-4710-8019"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Han","raw_affiliation_strings":["College of Software, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0003-4710-8019","affiliations":[{"raw_affiliation_string":"College of Software, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104331801","display_name":"Xunzhi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunzhi Wang","raw_affiliation_strings":["College of Software, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0000-5745-3914","affiliations":[{"raw_affiliation_string":"College of Software, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109735402","display_name":"Bitong Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bitong Luo","raw_affiliation_strings":["College of Software, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0002-2268-0193","affiliations":[{"raw_affiliation_string":"College of Software, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057020778","display_name":"Hang Gao","orcid":"https://orcid.org/0000-0003-4797-3072"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Gao","raw_affiliation_strings":["College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-4797-3072","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, China","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044042138","display_name":"Minlie Huang","orcid":"https://orcid.org/0000-0001-7111-1849"},"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":"Minlie Huang","raw_affiliation_strings":["Tsinghua University, TianJin, China"],"raw_orcid":"https://orcid.org/0000-0001-7111-1849","affiliations":[{"raw_affiliation_string":"Tsinghua University, TianJin, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048141765","display_name":"Mengting Hu","orcid":"https://orcid.org/0000-0003-1536-5400"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengting Hu","raw_affiliation_strings":["College of Software, Nankai University, Tianjin, China and Tianjin Key Laboratory of Software Experience and Human Computer Interaction, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-1536-5400","affiliations":[{"raw_affiliation_string":"College of Software, Nankai University, Tianjin, China and Tianjin Key Laboratory of Software Experience and Human Computer Interaction, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"782","last_page":"791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965000152587891,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9921000003814697,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6804437041282654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6645928025245667},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6537665724754333},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6400496363639832},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4639512896537781},{"id":"https://openalex.org/keywords/cold-start","display_name":"Cold start (automotive)","score":0.4479477107524872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44705408811569214},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3789924681186676},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34920844435691833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10896790027618408},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10044941306114197}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6804437041282654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6645928025245667},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6537665724754333},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6400496363639832},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4639512896537781},{"id":"https://openalex.org/C2778956030","wikidata":"https://www.wikidata.org/wiki/Q5142477","display_name":"Cold start (automotive)","level":2,"score":0.4479477107524872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44705408811569214},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3789924681186676},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34920844435691833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10896790027618408},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10044941306114197},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3729992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729992","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729992","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3729992","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3729992","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3729992","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G2639835172","display_name":null,"funder_award_id":"62406151","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412394942.pdf","grobid_xml":"https://content.openalex.org/works/W4412394942.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2070246124","https://openalex.org/W2251939518","https://openalex.org/W2293502436","https://openalex.org/W2797779452","https://openalex.org/W2896457183","https://openalex.org/W2903908313","https://openalex.org/W2954580219","https://openalex.org/W2970641574","https://openalex.org/W2979826702","https://openalex.org/W3101345273","https://openalex.org/W3105928338","https://openalex.org/W3156636935","https://openalex.org/W3176586352","https://openalex.org/W3177379791","https://openalex.org/W3198571508","https://openalex.org/W3210129272","https://openalex.org/W4224939570","https://openalex.org/W4224952733","https://openalex.org/W4285065369","https://openalex.org/W4285206744","https://openalex.org/W4287075708","https://openalex.org/W4319163914","https://openalex.org/W4384828482","https://openalex.org/W4385570190","https://openalex.org/W4385571896","https://openalex.org/W4387490658","https://openalex.org/W4393159567","https://openalex.org/W6601247122","https://openalex.org/W6798494020"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W3200375535"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2],"usually":[3,44],"require":[4],"large":[5],"labeled":[6],"datasets":[7],"to":[8,63,156,189],"generalize":[9],"well,":[10],"but":[11],"this":[12,40],"is":[13],"computationally":[14],"and":[15,52,86,152,173,201,213],"financially":[16],"costly.":[17],"Cold-start":[18],"few-shot":[19],"data":[20,36,48,69,74,180],"selection":[21],"enables":[22],"fast":[23],"model":[24,108],"generalization":[25,88],"by":[26,99],"selecting":[27],"a":[28,60,121,129],"few":[29],"diverse,":[30],"representative":[31],"samples":[32,119],"from":[33,55,181],"an":[34],"unlabeled":[35],"pool.":[37],"To":[38,123],"achieve":[39],"goal,":[41],"previous":[42],"work":[43],"divides":[45],"the":[46,72,79,102,115,166,182],"training":[47,73],"into":[49,169],"several":[50],"clusters":[51,168,184],"performs":[53],"sampling":[54],"these":[56,91,125,163],"clusters.":[57],"Yet,":[58],"such":[59],"way":[61],"tends":[62],"have":[64],"two":[65],"issues.":[66],"First,":[67],"imbalanced":[68,202,214],"distribution":[70],"in":[71,78,96],"pool":[75],"still":[76],"exists":[77],"selected":[80],"subset,":[81],"causing":[82],"models'":[83],"performance":[84],"biases":[85],"suboptimal":[87],"ability.":[89],"Second,":[90],"methods":[92],"improve":[93],"sample":[94,179],"diversity":[95],"each":[97],"cluster":[98],"considering":[100],"either":[101],"feature":[103],"dissimilarity":[104],"among":[105],"instances,":[106],"or":[107],"uncertainty":[109],"for":[110,136,149],"individual":[111],"instance.":[112],"They":[113],"ignore":[114],"entire":[116],"representativeness":[117],"of":[118],"within":[120,165],"cluster.":[122],"tackle":[124],"challenges,":[126],"we":[127,142,178],"propose":[128],"novel":[130],"framework":[131],"HCDS":[132,206],":":[133],"Hierarchical":[134],"Clustering":[135],"Cold-Start":[137],"Few-Shot":[138],"Data":[139],"Selection.":[140],"Specifically,":[141],"first":[143],"perform":[144,174],"class-level":[145,167],"clustering,":[146],"using":[147],"pseudo-labels":[148],"class":[150],"supervision":[151],"applying":[153],"contrastive":[154],"clustering":[155],"derive":[157],"class-rich":[158],"features.":[159],"We":[160],"then":[161],"refine":[162],"features":[164,172],"semantically":[170],"meaningful":[171],"representation-level":[175,183],"clustering.":[176],"Finally,":[177],"based":[185],"on":[186,194],"global":[187],"similarity":[188],"ensure":[190],"representativeness.":[191],"Experimental":[192],"results":[193],"six":[195],"public":[196],"datasets,":[197],"including":[198],"both":[199],"balanced":[200],"ones,":[203],"show":[204],"that":[205],"achieves":[207],"state-of-the-art":[208],"performance,":[209],"particularly":[210],"with":[211],"limited":[212],"data.":[215]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}