{"id":"https://openalex.org/W7203602002","doi":"https://doi.org/10.48550/arxiv.2608.14177","title":"Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction","display_name":"Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction","publication_year":2026,"publication_date":"2026-08-14","ids":{"openalex":"https://openalex.org/W7203602002","doi":"https://doi.org/10.48550/arxiv.2608.14177"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.14177","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14177","pdf_url":"https://arxiv.org/pdf/2608.14177","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.14177","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140206784","display_name":"Xuanmian He","orcid":"https://orcid.org/0009-0002-5878-3346","observed_orcids":["https://orcid.org/0009-0002-5878-3346"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xuanmian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147353001","display_name":"Can Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Can","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5147344890","display_name":"Wanjing Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Wanjing","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/T11344","display_name":"Traffic Prediction and Management Techniques","score":1.0,"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":1.0,"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/T10524","display_name":"Traffic control and management","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0,"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/traffic-flow-prediction","display_name":"traffic flow prediction","score":0.9980000257492065},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.7950000166893005},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.7789999842643738},{"id":"https://openalex.org/keywords/spatio-temporal-modeling","display_name":"spatio-temporal modeling","score":0.7770000100135803},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6259999871253967},{"id":"https://openalex.org/keywords/infonce","display_name":"InfoNCE","score":0.6639999747276306},{"id":"https://openalex.org/keywords/post-hoc-explanation","display_name":"post-hoc explanation","score":0.6019999980926514},{"id":"https://openalex.org/keywords/spurious-correlations","display_name":"spurious correlations","score":0.5950000286102295}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9153000116348267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633000016212463},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6798999905586243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328999757766724},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.14177","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14177","pdf_url":"https://arxiv.org/pdf/2608.14177","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.2608.14177","doi":"https://doi.org/10.48550/arxiv.2608.14177","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.14177","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.14177","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14177","pdf_url":"https://arxiv.org/pdf/2608.14177","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":[{"score":0.761900007724762,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"},{"score":0.428600013256073,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"sustainable_development_goals_aurora":[{"score":0.7726155519485474,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"spatiotemporal":[1,26,132],"models":[2,35],"integrating":[3],"graph":[4],"convolutions":[5],"and":[6,57,72,159,182],"attention":[7,133],"mechanisms":[8,64],"have":[9],"demonstrated":[10],"excellent":[11],"performance":[12],"in":[13,36,69],"network-level":[14],"traffic":[15,66,118,211],"flow":[16],"prediction,":[17],"owing":[18],"to":[19,23,59,110,134,174],"their":[20,29,43],"exceptional":[21],"ability":[22],"capture":[24],"complex":[25],"dependencies.":[27],"Despite":[28],"predictive":[30,183,197],"success,":[31],"deployment":[32],"of":[33,46,117,142,210],"such":[34],"safety-critical":[37],"urban":[38],"systems":[39],"remains":[40],"constrained":[41],"by":[42,151],"inherent":[44],"lack":[45],"transparency.":[47],"Existing":[48],"post-hoc":[49],"diagnostic":[50],"methods":[51],"often":[52],"struggle":[53],"with":[54,155,206],"spurious":[55],"correlations":[56],"fail":[58],"unveil":[60],"the":[61,83,112,129,143,176,207],"intrinsic":[62],"decision-making":[63,145],"governing":[65],"dynamics,":[67],"resulting":[68],"suboptimal":[70],"interpretability":[71,202],"limited":[73],"operational":[74],"trustworthiness.":[75],"To":[76],"address":[77],"these":[78],"challenges,":[79],"this":[80,135],"paper":[81],"proposes":[82],"Structure-Guided":[84],"Spatiotemporal":[85],"Attention":[86],"Graph":[87,108],"Neural":[88],"Network":[89],"(SGSAN).":[90],"Departing":[91],"from":[92],"traditional":[93],"architectures":[94],"that":[95,127,193,203],"rely":[96],"on":[97,162,188],"unconstrained":[98],"adaptive":[99],"graphs,":[100],"SGSAN":[101,194],"explicitly":[102],"learns":[103],"a":[104,139,167],"static":[105],"Directed":[106],"Dependency":[107],"(DDG)":[109],"identify":[111],"invariant":[113],"macroscopic":[114,157],"propagation":[115],"paths":[116],"states.":[119],"We":[120],"further":[121],"introduce":[122],"an":[123],"InfoNCE-based":[124],"soft-coupling":[125],"mechanism":[126],"anchors":[128],"model's":[130,144],"dynamic":[131],"structural":[136,180],"prior,":[137],"offering":[138],"mechanistic":[140],"account":[141],"process":[146],"while":[147,199],"ensuring":[148],"robust":[149],"forecasting":[150],"aligning":[152],"attention-based":[153],"reasoning":[154],"identified":[156],"dependencies":[158],"preventing":[160],"over-reliance":[161],"ephemeral":[163],"local":[164],"noise.":[165],"Furthermore,":[166],"decoupled":[168],"two-stage":[169],"optimization":[170],"framework":[171],"is":[172],"developed":[173],"resolve":[175],"fundamental":[177],"conflict":[178],"between":[179],"discovery":[181],"error":[184],"minimization.":[185],"Extensive":[186],"experiments":[187],"multiple":[189],"real-world":[190],"datasets":[191],"demonstrate":[192],"achieves":[195],"state-of-the-art":[196],"accuracy":[198],"providing":[200],"built-in":[201],"organically":[204],"aligns":[205],"physical":[208],"logic":[209],"networks.":[212]},"counts_by_year":[],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2026-08-18T00:00:00"}