{"id":"https://openalex.org/W7154956138","doi":"https://doi.org/10.48550/arxiv.2604.15838","title":"Reversible Residual Normalization Alleviates Spatio-Temporal Distribution Shift","display_name":"Reversible Residual Normalization Alleviates Spatio-Temporal Distribution Shift","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7154956138","doi":"https://doi.org/10.48550/arxiv.2604.15838"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.15838","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15838","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.2604.15838","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133892744","display_name":"Zhaobo Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zhaobo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134081337","display_name":"Vincent Gauthier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gauthier, Vincent","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134047403","display_name":"Mehdi Naima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naima, Mehdi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.5583999752998352,"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":0.5583999752998352,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.13169999420642853,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.045899998396635056,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8273000121116638},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7128000259399414},{"id":"https://openalex.org/keywords/invertible-matrix","display_name":"Invertible matrix","score":0.6238999962806702},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5170000195503235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3894999921321869},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.3650999963283539}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8273000121116638},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7128000259399414},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.6238999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5544999837875366},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5094000101089478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43470001220703125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3395000100135803},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C2776800370","wikidata":"https://www.wikidata.org/wiki/Q5172864","display_name":"Correlative","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.15838","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15838","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.2604.15838","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15838","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Distribution":[0],"shift":[1,45,97],"severely":[2],"degrades":[3],"the":[4,25,56,66,119],"performance":[5],"of":[6,58,150],"deep":[7],"forecasting":[8,177],"models.":[9],"While":[10],"this":[11,78],"issue":[12],"is":[13,49],"well-studied":[14],"for":[15,176],"individual":[16,59],"time":[17],"series,":[18],"it":[19],"remains":[20],"a":[21,47,86,144,158,171],"significant":[22],"challenge":[23],"in":[24,98,143,157],"spatio-temporal":[26,180],"domain.":[27],"Effective":[28],"solutions":[29],"like":[30],"instance":[31],"normalization":[32,116],"and":[33,101,138,162,173],"its":[34],"variants":[35],"can":[36],"mitigate":[37],"temporal":[38,102],"shifts":[39],"by":[40],"standardizing":[41],"statistics.":[42],"However,":[43],"distribution":[44,96],"on":[46,178],"graph":[48,107,121,132],"far":[50],"more":[51],"complex,":[52],"involving":[53],"not":[54],"only":[55],"drift":[57],"node":[60],"series":[61],"but":[62],"also":[63],"heterogeneity":[64],"across":[65],"spatial":[67,100],"network":[68],"where":[69],"different":[70],"nodes":[71],"exhibit":[72],"distinct":[73],"statistical":[74],"properties.":[75],"To":[76],"tackle":[77],"problem,":[79],"we":[80],"propose":[81],"Reversible":[82],"Residual":[83],"Normalization":[84,129],"(RRN),":[85],"novel":[87],"framework":[88,152],"that":[89,117],"performs":[90],"spatially-aware":[91],"invertible":[92,111],"transformations":[93],"to":[94,155],"address":[95],"both":[99],"dimensions.":[103],"Our":[104],"approach":[105],"integrates":[106],"convolutional":[108],"operations":[109],"within":[110],"residual":[112],"blocks,":[113],"enabling":[114],"adaptive":[115],"respects":[118],"underlying":[120],"structure":[122],"while":[123],"maintaining":[124],"reversibility.":[125],"By":[126],"combining":[127],"Center":[128],"with":[130],"spectral-constrained":[131],"neural":[133],"networks,":[134],"our":[135,151],"method":[136],"captures":[137],"normalizes":[139],"complex":[140],"Spatio-Temporal":[141],"relationships":[142],"data-driven":[145],"manner.":[146],"The":[147],"bidirectional":[148],"nature":[149],"allows":[153],"models":[154],"learn":[156],"normalized":[159],"latent":[160],"space":[161],"recover":[163],"original":[164],"distributional":[165],"properties":[166],"through":[167],"inverse":[168],"transformation,":[169],"offering":[170],"robust":[172],"model-agnostic":[174],"solution":[175],"dynamic":[179],"systems.":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-21T00:00:00"}