{"id":"https://openalex.org/W7162416775","doi":"https://doi.org/10.48550/arxiv.2605.24911","title":"Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting","display_name":"Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162416775","doi":"https://doi.org/10.48550/arxiv.2605.24911"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.24911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24911","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.24911","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136992954","display_name":"Jinjin Chi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi, Jinjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137004367","display_name":"Lei Feng","orcid":"https://orcid.org/0000-0001-5703-5923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136998316","display_name":"Lulu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lulu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137021355","display_name":"Yongcheng Jing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Yongcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137066288","display_name":"Yiming Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137025182","display_name":"Ximing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ximing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026951130","display_name":"Jialie Shen","orcid":"https://orcid.org/0000-0002-4560-8509"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Jialie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136992937","display_name":"Leszek Rutkowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rutkowski, Leszek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137037131","display_name":"Dacheng Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Dacheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"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/T11918","display_name":"Forecasting Techniques and Applications","score":0.6337000131607056,"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/T11918","display_name":"Forecasting Techniques and Applications","score":0.6337000131607056,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.06400000303983688,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.05249999836087227,"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/robustness","display_name":"Robustness (evolution)","score":0.6769000291824341},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6201000213623047},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4690000116825104},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.4602999985218048},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.45570001006126404},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.44839999079704285},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42730000615119934}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6769000291824341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6276000142097473},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4690000116825104},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.45570001006126404},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42730000615119934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41600000858306885},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2793999910354614},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2535000145435333},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.24911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24911","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":"doi:10.48550/arxiv.2605.24911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24911","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":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":{"Time":[0],"series":[1,41,84],"foundation":[2],"models":[3],"(TSFMs)":[4],"have":[5],"recently":[6],"achieved":[7],"strong":[8],"zero-shot":[9,217],"forecasting":[10,218],"performance":[11,37],"through":[12],"large-scale":[13],"pretraining":[14],"and":[15,118,136,149,176,178,188,209,213],"retrieval-augmented":[16],"prediction.":[17],"However,":[18],"our":[19,201],"empirical":[20],"analysis":[21],"reveals":[22],"a":[23,77,112,121,137],"non-trivial":[24],"limitation":[25],"of":[26],"retrieval-based":[27,214],"forecasting:":[28],"retrieval":[29,89,184],"tends":[30],"to":[31,104,125,157,164],"induce":[32],"more":[33],"oscillatory":[34],"predictions,":[35],"improving":[36],"on":[38,45],"highly":[39],"fluctuating":[40],"while":[42,161],"degrading":[43],"accuracy":[44],"smoother,":[46],"trend-dominated":[47],"ones.":[48],"This":[49],"suggests":[50],"that":[51,172,183,200],"retrieved":[52,96],"information":[53],"may":[54],"be":[55],"fused":[56,150],"into":[57,128],"prediction":[58],"without":[59,193],"explicitly":[60],"distinguishing":[61],"stable":[62,133],"temporal":[63],"structure":[64,135],"from":[65,101],"instance-specific":[66],"variations,":[67],"which":[68],"can":[69],"reduce":[70],"robustness":[71,205],"under":[72,206],"distribution":[73,207],"shifts.":[74],"We":[75,167],"propose":[76],"Retrieval-guided":[78],"Invariant-Dynamic":[79],"DEcomposition":[80],"framework":[81],"for":[82,151],"time":[83],"forecasting.":[85],"Rather":[86],"than":[87],"using":[88],"as":[90,98],"auxiliary":[91],"predictive":[92],"context,":[93],"we":[94,109],"leverage":[95],"sequences":[97],"implicit":[99],"samples":[100],"related":[102],"environments":[103],"guide":[105],"representation":[106,114,191],"decomposition.":[107],"Specifically,":[108],"first":[110],"construct":[111],"retrieval-aware":[113],"via":[115],"attention-based":[116],"aggregation,":[117],"then":[119],"introduce":[120],"retrieval-guided":[122],"routing":[123],"mechanism":[124],"decompose":[126],"it":[127],"an":[129],"invariant":[130,174,190],"component":[131,139],"capturing":[132],"shared":[134],"dynamic":[138],"modeling":[140],"context-dependent":[141],"variations.":[142],"These":[143],"two":[144],"components":[145],"are":[146],"forecast":[147],"separately":[148],"final":[152],"prediction,":[153],"enabling":[154],"the":[155],"model":[156],"preserve":[158],"transferable":[159],"patterns":[160],"remaining":[162],"adaptive":[163],"evolving":[165],"dynamics.":[166],"further":[168],"design":[169],"training":[170],"objectives":[171],"encourage":[173],"learning":[175,192],"disentanglement,":[177],"provide":[179],"theoretical":[180],"insight":[181],"showing":[182],"aggregation":[185],"reduces":[186],"variance":[187],"approximates":[189],"explicit":[194],"environment":[195],"supervision.":[196],"Extensive":[197],"experiments":[198],"demonstrate":[199],"method":[202],"consistently":[203],"improves":[204],"shifts":[208],"outperforms":[210],"existing":[211],"TSFMs":[212],"baselines":[215],"in":[216],"settings.":[219]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-27T00:00:00"}