{"id":"https://openalex.org/W7171958753","doi":"https://doi.org/10.1145/3770854.3780218","title":"TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation","display_name":"TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7171958753","doi":"https://doi.org/10.1145/3770854.3780218"},"language":null,"primary_location":{"id":"doi:10.1145/3770854.3780218","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780218","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770854.3780218","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101769931","display_name":"Juntong Ni","orcid":"https://orcid.org/0009-0006-7070-8137"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juntong Ni","raw_affiliation_strings":["Emory University, Atlanta, USA"],"raw_orcid":"https://orcid.org/0009-0006-7070-8137","affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139671497","display_name":"Zewen Liu","orcid":"https://orcid.org/0009-0001-1147-4274"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zewen Liu","raw_affiliation_strings":["Emory University, Atlanta, USA"],"raw_orcid":"https://orcid.org/0009-0001-1147-4274","affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056134655","display_name":"Shiyu Wang","orcid":"https://orcid.org/0000-0001-5376-6761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Wang","raw_affiliation_strings":["Independent Researcher, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5376-6761","affiliations":[{"raw_affiliation_string":"Independent Researcher, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101811842","display_name":"Ming Jin","orcid":"https://orcid.org/0000-0002-6833-4811"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ming Jin","raw_affiliation_strings":["Griffith University, Brisbane, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6833-4811","affiliations":[{"raw_affiliation_string":"Griffith University, Brisbane, Australia","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100758371","display_name":"Wei Jin","orcid":"https://orcid.org/0000-0002-5054-954X"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Jin","raw_affiliation_strings":["Emory University, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0002-5054-954X","affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, USA","institution_ids":["https://openalex.org/I150468666"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1113","last_page":"1124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.623199999332428},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6154000163078308},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5496000051498413},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.5217000246047974},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.4986000061035156},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.47999998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922999858856201},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.623199999332428},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6154000163078308},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4918000102043152},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4505999982357025},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4214000105857849},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3770854.3780218","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780218","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3770854.3780218","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780218","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W3081030157","https://openalex.org/W3123191313","https://openalex.org/W3177318507","https://openalex.org/W3214511793","https://openalex.org/W4319781637","https://openalex.org/W4365791115","https://openalex.org/W4379382937","https://openalex.org/W4381328595","https://openalex.org/W4382203079","https://openalex.org/W4382239356","https://openalex.org/W4392366670","https://openalex.org/W4401201975","https://openalex.org/W4412877071"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"and":[1,16,51,57,127,141],"CNN-based":[2],"methods":[3],"demonstrate":[4],"strong":[5],"performance":[6,108],"in":[7,54],"long-term":[8],"time":[9],"series":[10],"forecasting.":[11],"However,":[12],"their":[13],"high":[14],"computational":[15],"storage":[17],"requirements":[18],"can":[19,45,94],"hinder":[20],"large-scale":[21],"deployment.":[22],"To":[23],"address":[24],"this":[25,62],"limitation,":[26],"we":[27,64,84,133],"propose":[28],"integrating":[29],"lightweight":[30],"MLP":[31,107],"with":[32],"advanced":[33],"architectures":[34],"using":[35],"knowledge":[36],"distillation":[37],"(KD).":[38],"Our":[39],"preliminary":[40],"study":[41],"reveals":[42],"different":[43],"models":[44,77,115],"capture":[46],"complementary":[47],"patterns,":[48],"particularly":[49],"multi-scale":[50],"multi-period":[52],"patterns":[53,74],"the":[55,139],"temporal":[56],"frequency":[58],"domains.":[59],"Based":[60],"on":[61,116],"observation,":[63],"introduce":[65],"TimeDistill,":[66],"a":[67,86,98],"cross-architecture":[68],"KD":[69,92],"framework":[70],"that":[71,90],"transfers":[72],"these":[73],"from":[75],"teacher":[76,114],"(e.g.,":[78],"Transformers,":[79],"CNNs)":[80],"to":[81,111,123,137],"MLP.":[82],"Additionally,":[83],"provide":[85],"theoretical":[87],"analysis,":[88],"demonstrating":[89],"our":[91],"approach":[93],"be":[95],"interpreted":[96],"as":[97],"specialized":[99],"form":[100],"of":[101,143],"mixup":[102],"data":[103],"augmentation.":[104],"TimeDistill":[105],"improves":[106],"by":[109],"up":[110,122],"18.6%,":[112],"surpassing":[113],"eight":[117],"datasets.":[118],"It":[119],"also":[120],"achieves":[121],"7X":[124],"faster":[125],"inference":[126],"requires":[128],"130X":[129],"fewer":[130],"parameters.":[131],"Furthermore,":[132],"conduct":[134],"extensive":[135],"evaluations":[136],"highlight":[138],"versatility":[140],"effectiveness":[142],"TimeDistill.":[144],"The":[145],"code":[146],"is":[147],"available":[148],"at":[149],"Github":[150],"Code":[151],"Repo.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-08-01T00:00:00"}