{"id":"https://openalex.org/W4381245607","doi":"https://doi.org/10.1145/3580305.3599533","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","display_name":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4381245607","doi":"https://doi.org/10.1145/3580305.3599533"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599533","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599533","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599533","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054052378","display_name":"Vijay Ekambaram","orcid":"https://orcid.org/0009-0004-5824-9826"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Vijay Ekambaram","raw_affiliation_strings":["IBM Research, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067289130","display_name":"Arindam Jati","orcid":"https://orcid.org/0000-0002-9498-8536"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arindam Jati","raw_affiliation_strings":["IBM Research, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM Research, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562820","display_name":"Nam Nguyen","orcid":"https://orcid.org/0009-0008-6981-4463"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Nguyen","raw_affiliation_strings":["IBM Research, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074096341","display_name":"Phanwadee Sinthong","orcid":"https://orcid.org/0009-0006-4423-3860"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phanwadee Sinthong","raw_affiliation_strings":["IBM Research, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057936833","display_name":"Jayant Kalagnanam","orcid":"https://orcid.org/0009-0009-5051-2606"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayant Kalagnanam","raw_affiliation_strings":["IBM Research, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054052378"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":51.4546,"has_fulltext":true,"cited_by_count":207,"citation_normalized_percentile":{"value":0.99957476,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"459","last_page":"469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9943000078201294,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7794517278671265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6098564267158508},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5547258257865906},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5353823900222778},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5060741305351257},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.463441401720047},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4118974804878235},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33563894033432007},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32137763500213623},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1363934874534607},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08694535493850708}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794517278671265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6098564267158508},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5547258257865906},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5353823900222778},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5060741305351257},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.463441401720047},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4118974804878235},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33563894033432007},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32137763500213623},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1363934874534607},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08694535493850708},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3580305.3599533","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599533","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599533","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.09364","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.09364","pdf_url":"https://arxiv.org/pdf/2306.09364","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599533","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599533","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599533","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381245607.pdf","grobid_xml":"https://content.openalex.org/works/W4381245607.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W2133564696","https://openalex.org/W2194775991","https://openalex.org/W2612690371","https://openalex.org/W2772433304","https://openalex.org/W2811507150","https://openalex.org/W2896457183","https://openalex.org/W3157506437","https://openalex.org/W3163465952","https://openalex.org/W3169210662","https://openalex.org/W3169661950","https://openalex.org/W3170863103","https://openalex.org/W3177318507","https://openalex.org/W3183804933","https://openalex.org/W3190152617","https://openalex.org/W3195577433","https://openalex.org/W3198648680","https://openalex.org/W3199148273","https://openalex.org/W3209374680","https://openalex.org/W3212890323","https://openalex.org/W3217099242","https://openalex.org/W4206173445","https://openalex.org/W4223929908","https://openalex.org/W4225494949","https://openalex.org/W4281752007","https://openalex.org/W4283823780","https://openalex.org/W4285602653","https://openalex.org/W4287116209","https://openalex.org/W4287184379","https://openalex.org/W4297808394","https://openalex.org/W4300900294","https://openalex.org/W4310416691","https://openalex.org/W4310421036","https://openalex.org/W4312853765","https://openalex.org/W4320352504","https://openalex.org/W4324144701","https://openalex.org/W4382203079","https://openalex.org/W4385245566","https://openalex.org/W4394666973","https://openalex.org/W6796417832","https://openalex.org/W6863951927"],"related_works":["https://openalex.org/W2076543106","https://openalex.org/W3158157485","https://openalex.org/W2523437662","https://openalex.org/W89844371","https://openalex.org/W2019891950","https://openalex.org/W2789124470","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W3000407446","https://openalex.org/W4387048144"],"abstract_inverted_index":{"Transformers":[0],"have":[1],"gained":[2],"popularity":[3],"in":[4,31,81,89,152,165,226,250],"time":[5,63,94],"series":[6,95],"forecasting":[7,57,227],"for":[8,25,55,93,119,215],"their":[9,16],"ability":[10],"to":[11,69,101,115,138,168],"capture":[12],"long-sequence":[13],"interactions.":[14],"However,":[15],"memory":[17,251],"and":[18,58,96,128,144,204,223,252],"compute-intensive":[19],"requirements":[20],"pose":[21],"a":[22,41,106,133,149,158,211,229,247],"critical":[23],"bottleneck":[24],"long-term":[26],"forecasting,":[27],"despite":[28],"numerous":[29],"advancements":[30],"compute-aware":[32],"self-attention":[33],"modules.":[34,51],"To":[35],"address":[36],"this,":[37],"we":[38,177],"propose":[39,132],"TSMixer,":[40],"lightweight":[42,175],"neural":[43],"architecture":[44],"exclusively":[45],"composed":[46],"of":[47,78,110,183,232,241],"multi-layer":[48],"perceptron":[49],"(MLP)":[50],"TSMixer":[52,219],"is":[53,163],"designed":[54],"multivariate":[56],"representation":[59],"learning":[60,181,207],"on":[61],"patched":[62],"series,":[64],"providing":[65],"an":[66],"efficient":[67],"alternative":[68],"Transformers.":[70],"Our":[71],"model":[72],"draws":[73],"inspiration":[74],"from":[75],"the":[76,86,116,122,166,180,237],"success":[77],"MLP-Mixer":[79,92,117],"models":[80,190,225,243],"computer":[82],"vision.":[83],"We":[84,130],"demonstrate":[85],"challenges":[87],"involved":[88],"adapting":[90],"Vision":[91],"introduce":[97],"empirically":[98],"validated":[99],"components":[100],"enhance":[102,179],"accuracy.":[103],"This":[104],"includes":[105],"novel":[107],"design":[108,198],"paradigm":[109],"attaching":[111],"online":[112],"reconciliation":[113],"heads":[114],"backbone,":[118],"explicitly":[120],"modeling":[121,136],"time-series":[123,216],"properties":[124],"such":[125],"as":[126],"hierarchy":[127],"channel-correlations.":[129],"also":[131,235],"Hybrid":[134],"channel":[135,142],"approach":[137],"effectively":[139],"handle":[140],"noisy":[141],"interactions":[143],"generalization":[145],"across":[146],"diverse":[147],"datasets,":[148],"common":[150],"challenge":[151],"existing":[153],"patch":[154],"channel-mixing":[155],"methods.":[156],"Additionally,":[157],"simple":[159,184],"gated":[160],"attention":[161],"mechanism":[162],"introduced":[164],"backbone":[167],"prioritize":[169],"important":[170],"features.":[171],"By":[172],"incorporating":[173],"these":[174],"components,":[176],"significantly":[178],"capability":[182],"MLP":[185,222],"structures,":[186],"outperforming":[187],"complex":[188],"Transformer":[189,224],"with":[191,201,246],"minimal":[192],"computing":[193],"usage.":[194],"Moreover,":[195],"TSMixer's":[196],"modular":[197],"enables":[199],"compatibility":[200],"both":[202],"supervised":[203],"masked":[205],"self-supervised":[206],"methods,":[208],"making":[209],"it":[210],"promising":[212],"building":[213],"block":[214],"Foundation":[217],"Models.":[218],"outperforms":[220,236],"state-of-the-art":[221],"by":[228],"considerable":[230],"margin":[231],"8-60%.":[233],"It":[234],"latest":[238],"strong":[239],"benchmarks":[240],"Patch-Transformer":[242],"(by":[244],"1-2%)":[245],"significant":[248],"reduction":[249],"runtime":[253],"(2-3X).":[254]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":137},{"year":2024,"cited_by_count":53},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}