{"id":"https://openalex.org/W7126280403","doi":"https://doi.org/10.48550/arxiv.2601.21866","title":"MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts","display_name":"MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126280403","doi":"https://doi.org/10.48550/arxiv.2601.21866"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2601.21866","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124451780","display_name":"Evandro S. Ortigossa","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ortigossa, Evandro S.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124346736","display_name":"Guy Lutsker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lutsker, Guy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124328709","display_name":"Eran Segal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Segal, Eran","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5124451780"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.2985000014305115,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.2985000014305115,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11918","display_name":"Forecasting Techniques and Applications","score":0.1265999972820282,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.08839999884366989,"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/multivariate-statistics","display_name":"Multivariate statistics","score":0.6240000128746033},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6154000163078308},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.559499979019165},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.5554999709129333},{"id":"https://openalex.org/keywords/covariate","display_name":"Covariate","score":0.45249998569488525},{"id":"https://openalex.org/keywords/univariate","display_name":"Univariate","score":0.42730000615119934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7153000235557556},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.6240000128746033},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6154000163078308},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4772999882698059},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44699999690055847},{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.42730000615119934},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38339999318122864},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2601.21866","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2601.21866","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.21866","pdf_url":null,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2601.21866","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"multivariate":[1,142],"time":[2,46],"series":[3,47],"can":[4],"exhibit":[5],"intricate":[6],"multi-scale":[7],"structures,":[8],"including":[9],"global":[10],"trends,":[11],"local":[12],"periodicities,":[13],"and":[14,29,127,144],"non-stationary":[15,96],"regimes,":[16],"which":[17],"makes":[18],"long-horizon":[19],"forecasting":[20],"challenging.":[21],"Although":[22],"sparse":[23,60],"Mixture-of-Experts":[24],"(MoE)":[25],"approaches":[26],"improve":[27],"scalability":[28],"specialization,":[30],"they":[31],"typically":[32],"rely":[33],"on":[34],"homogeneous":[35],"MLP":[36],"experts":[37,86],"that":[38,58],"poorly":[39],"capture":[40],"the":[41,154],"diverse":[42],"temporal":[43,66],"dynamics":[44,97],"of":[45,72],"data.":[48],"We":[49,138],"address":[50],"these":[51],"limitations":[52],"with":[53,83,115,147],"MoHETS,":[54],"an":[55],"encoder-only":[56],"Transformer":[57],"integrates":[59],"Mixture-of-Heterogeneous-Experts":[61],"(MoHE)":[62],"layers.":[63],"MoHE":[64],"routes":[65],"patches":[67],"to":[68,95,132,160],"a":[69,76,116,129],"small":[70],"subset":[71],"expert":[73,79],"networks,":[74],"combining":[75],"shared":[77],"depthwise-convolution":[78],"for":[80,87,168],"sequence-level":[81],"continuity":[82],"routed":[84],"Fourier-based":[85],"patch-level":[88],"periodic":[89],"structures.":[90],"MoHETS":[91,148],"further":[92],"improves":[93],"robustness":[94],"by":[98,157],"incorporating":[99],"exogenous":[100],"information":[101],"via":[102],"cross-attention":[103],"over":[104],"covariate":[105],"patch":[106,119],"embeddings.":[107],"Finally,":[108],"we":[109],"replace":[110],"parameter-heavy":[111],"linear":[112],"projection":[113],"heads":[114],"lightweight":[117],"convolutional":[118],"decoder,":[120],"improving":[121],"parameter":[122],"efficiency,":[123],"reducing":[124,153],"training":[125],"instability,":[126],"allowing":[128],"single":[130],"model":[131],"generalize":[133],"across":[134,140],"arbitrary":[135],"forecast":[136],"horizons.":[137],"validate":[139],"seven":[141],"benchmarks":[143],"multiple":[145],"horizons,":[146],"consistently":[149],"achieving":[150],"state-of-the-art":[151],"performance,":[152],"average":[155],"MSE":[156],"$12\\%$":[158],"compared":[159],"strong":[161],"recent":[162],"baselines,":[163],"demonstrating":[164],"effective":[165],"heterogeneous":[166],"specialization":[167],"long-term":[169],"forecasting.":[170]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-01T00:00:00"}