{"id":"https://openalex.org/W7152422563","doi":"https://doi.org/10.48550/arxiv.2604.06727","title":"Bi-level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approach","display_name":"Bi-level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approach","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7152422563","doi":"https://doi.org/10.48550/arxiv.2604.06727"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06727","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06727","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.06727","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072469364","display_name":"Shengchao Chen","orcid":"https://orcid.org/0000-0001-9992-2264"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shengchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059227406","display_name":"Guodong Long","orcid":"https://orcid.org/0000-0003-3740-9515"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Guodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102773196","display_name":"Dikai Liu","orcid":"https://orcid.org/0000-0001-9398-2100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dikai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133298336","display_name":"Jing Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T13702","display_name":"Machine Learning in Healthcare","score":0.5838000178337097,"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":0.5838000178337097,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.059700001031160355,"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":0.056299999356269836,"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/federated-learning","display_name":"Federated learning","score":0.7516000270843506},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6822999715805054},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.5781999826431274},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.5770999789237976},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4772999882698059},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.42649999260902405},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.42329999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134999871253967},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.7516000270843506},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6822999715805054},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.5781999826431274},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4706999957561493},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44429999589920044},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.42329999804496765},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3873000144958496},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06727","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06727","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.06727","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06727","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4106423258781433,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Heterogeneity":[0],"in":[1,9,136,158],"time":[2,26],"series":[3,27,67],"data":[4],"is":[5],"more":[6],"pronounced":[7],"than":[8],"vision":[10],"or":[11],"language,":[12],"as":[13],"temporal":[14],"dynamics":[15],"vary":[16],"substantially":[17],"across":[18,118],"domains":[19],"and":[20,48,79,99,106,132,138],"tasks.":[21],"Existing":[22],"efforts":[23],"on":[24],"training":[25,154],"foundation":[28],"models":[29],"(TSFMs)":[30],"from":[31,65,156],"scratch":[32,157],"are":[33],"often":[34],"trained":[35,124],"with":[36,125],"mixed-batch":[37],"strategies":[38],"that":[39,61,92,122],"merge":[40],"large-scale":[41],"datasets,":[42],"which":[43],"can":[44],"cause":[45],"gradient":[46],"conflicts":[47,95],"degrade":[49],"representation":[50],"quality.":[51],"To":[52,81],"address":[53],"this,":[54],"we":[55,86],"propose":[56],"a":[57,88,150],"fine-grained":[58],"learning":[59,90],"method":[60,91,127],"distills":[62],"invariant":[63],"knowledge":[64],"heterogeneous":[66,159],"while":[68,141],"reducing":[69],"cross-domain":[70,112],"interference.":[71],"We":[72],"characterize":[73],"heterogeneity":[74],"at":[75,147],"two":[76],"levels:":[77],"inter-domain":[78,108],"intra-domain.":[80],"tackle":[82],"this":[83],"bi-level":[84],"heterogeneity,":[85],"design":[87],"federated":[89,133],"mitigates":[93],"intra-domain":[94],"by":[96,110],"enforcing":[97],"domain-invariant":[98],"semantically":[100],"consistent":[101],"representations":[102],"through":[103],"local":[104],"regularization,":[105],"addresses":[107],"discrepancies":[109],"enhancing":[111],"collaboration":[113],"via":[114],"domain-aware":[115],"aggregation.":[116],"Experiments":[117],"diverse":[119],"benchmarks":[120],"show":[121],"TSFMs":[123,155],"our":[126],"consistently":[128],"outperform":[129],"both":[130],"centralized":[131],"TSFM":[134],"baselines":[135],"point":[137],"probabilistic":[139],"forecasting,":[140],"also":[142],"achieving":[143],"competitive":[144],"zero-shot":[145],"performance":[146],"scale,":[148],"offering":[149],"flexible":[151],"pathway":[152],"for":[153],"environments.":[160]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-10T00:00:00"}