{"id":"https://openalex.org/W7224100233","doi":"https://doi.org/10.48550/arxiv.2610.37598","title":"GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting","display_name":"GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224100233","doi":"https://doi.org/10.48550/arxiv.2610.37598"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.37598","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37598","pdf_url":"https://arxiv.org/pdf/2610.37598","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.37598","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051027331","display_name":"Joseph Ross Ungar Natter","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natter, Joseph","raw_affiliation_strings":["Kennesaw State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160022549","display_name":"Long Vu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vu, Long","raw_affiliation_strings":["Kennesaw State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160037282","display_name":"Yifan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I119942284","display_name":"Missouri State University","ror":"https://ror.org/01d2sez20","country_code":"US","type":"education","lineage":["https://openalex.org/I119942284"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Yifan","raw_affiliation_strings":["Missouri State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri State University","institution_ids":["https://openalex.org/I119942284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160021824","display_name":"Bobin Deng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deng, Bobin","raw_affiliation_strings":["Kennesaw State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054721271","display_name":"Kun Suo","orcid":"https://orcid.org/0000-0001-8562-0492","observed_orcids":["https://orcid.org/0000-0001-8562-0492"]},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suo, Kun","raw_affiliation_strings":["Kennesaw State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160038677","display_name":"Rui Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Rui","raw_affiliation_strings":["Kennesaw State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kennesaw State University","institution_ids":["https://openalex.org/I172980758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":1.0,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prior-data-fitted-networks","display_name":"prior-data fitted networks","score":0.9570000171661377},{"id":"https://openalex.org/keywords/road-topology","display_name":"road network topology","score":0.6389999985694885},{"id":"https://openalex.org/keywords/random-walk-diffusion","display_name":"random walk diffusion","score":0.8799999952316284},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.7990000247955322},{"id":"https://openalex.org/keywords/spatiotemporal-interaction","display_name":"spatiotemporal interaction","score":0.8040000200271606},{"id":"https://openalex.org/keywords/sensor-networks","display_name":"sensor networks","score":0.6769999861717224},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7390999794006348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715399980545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321999788284302},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4878999888896942},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.42170000076293945},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.319599986076355},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.37598","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37598","pdf_url":"https://arxiv.org/pdf/2610.37598","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.37598","doi":"https://doi.org/10.48550/arxiv.2610.37598","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.37598","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.37598","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37598","pdf_url":"https://arxiv.org/pdf/2610.37598","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7250000238418579},{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.7207000255584717}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224100233.pdf","grobid_xml":"https://content.openalex.org/works/W7224100233.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7213060587","https://openalex.org/W7221573209","https://openalex.org/W6922463643","https://openalex.org/W4306254403","https://openalex.org/W4392388141","https://openalex.org/W4415002713","https://openalex.org/W4399881588","https://openalex.org/W4390492464","https://openalex.org/W4414615216","https://openalex.org/W7160273671"],"abstract_inverted_index":{"Traffic":[0],"forecasting":[1,66],"requires":[2],"modeling":[3,83],"complex":[4],"temporal":[5,135],"dynamics":[6,115,136],"and":[7,29,137,157,211,230],"the":[8,73,89,110,166],"spatial":[9],"dependencies":[10,75],"imposed":[11],"by":[12,48,172,187],"road":[13,99],"topology.":[14],"Supervised":[15],"graph-based":[16],"models":[17,203],"achieve":[18],"strong":[19],"performance,":[20],"but":[21],"are":[22],"often":[23],"trained":[24],"for":[25,61,147,239],"a":[26,45,127],"particular":[27],"dataset":[28],"sensor":[30],"graph,":[31],"making":[32],"deployment":[33],"to":[34,112,131,153,177,192],"new":[35],"or":[36],"evolving":[37],"networks":[38],"costly.":[39],"Prior-Data":[40,92],"Fitted":[41,93],"Networks":[42],"(PFNs)":[43],"offer":[44],"zero-shot":[46,85,197,240],"alternative":[47],"learning":[49,238],"in-context":[50,237],"inference":[51,120,231],"from":[52,217],"synthetic":[53,103],"task":[54,104],"priors,":[55],"which":[56],"provide":[57],"an":[58],"explicit":[59],"mechanism":[60],"encoding":[62],"domain-specific":[63],"assumptions.":[64],"Existing":[65],"PFNs,":[67],"however,":[68],"do":[69],"not":[70],"explicitly":[71],"represent":[72],"graph-structured":[74],"governing":[76],"traffic":[77,82,241],"dynamics.":[78],"To":[79],"combine":[80],"graph-aware":[81],"with":[84,233],"adaptation,":[86],"we":[87],"introduce":[88],"Graph-Aware":[90],"Spatiotemporal":[91],"Network":[94],"(GAS-PFN).":[95],"GAS-PFN":[96,152,169],"incorporates":[97],"sampled":[98],"topology":[100],"into":[101],"its":[102,179],"prior":[105],"through":[106,126],"random-walk":[107],"diffusion,":[108],"teaching":[109],"model":[111,133],"learn":[113],"graph-coupled":[114],"during":[116],"pretraining.":[117],"Its":[118],"co-designed":[119],"architecture":[121],"uses":[122],"two":[123],"mask-conditioned":[124],"passes":[125],"shared":[128],"Transformer":[129],"backbone":[130],"separately":[132],"sensor-specific":[134],"spatiotemporal":[138],"interactions":[139],"among":[140],"neighboring":[141],"sensors":[142],"before":[143],"integrating":[144],"their":[145],"representations":[146],"prediction.":[148],"This":[149],"design":[150],"enables":[151],"use":[154],"target-network":[155],"structure":[156,235],"context":[158,214],"without":[159],"parameter":[160],"updates.":[161],"Across":[162],"six":[163],"benchmarks":[164],"at":[165],"90-minute":[167],"horizon,":[168],"reduces":[170,185],"MSE":[171,186],"34.0%":[173],"on":[174,189],"average":[175,190],"relative":[176,191],"TimePFN,":[178],"closest":[180],"PFN-based":[181],"predecessor.":[182],"It":[183],"also":[184],"27.7%":[188],"four":[193],"recent":[194,209],"industry-developed":[195],"general-purpose":[196],"forecasters.":[198],"In":[199],"this":[200],"comparison,":[201],"all":[202],"receive":[204],"90":[205],"minutes":[206],"of":[207],"contiguous":[208],"history,":[210],"any":[212],"additional":[213],"is":[215],"drawn":[216],"each":[218],"dataset's":[219],"chronological":[220],"training":[221],"split.":[222],"These":[223],"results":[224],"indicate":[225],"that":[226],"aligning":[227],"PFN":[228],"priors":[229],"architectures":[232],"graph":[234],"improves":[236],"forecasting.":[242]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-29T00:00:00"}