{"id":"https://openalex.org/W7164521063","doi":"https://doi.org/10.48550/arxiv.2606.13119","title":"MP3: Multi-Period Pattern Pre-training for Spatio-Temporal Forecasting","display_name":"MP3: Multi-Period Pattern Pre-training for Spatio-Temporal Forecasting","publication_year":2026,"publication_date":"2026-06-11","ids":{"openalex":"https://openalex.org/W7164521063","doi":"https://doi.org/10.48550/arxiv.2606.13119"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.13119","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13119","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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.2606.13119","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138502724","display_name":"Lilan Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Lilan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138516943","display_name":"Yandi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yandi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138529816","display_name":"Qingren Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Qingren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032769556","display_name":"Chongshou Li","orcid":"https://orcid.org/0000-0002-7595-0997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chongshou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138519341","display_name":"Tianrui Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Tianrui","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":0.9200000166893005,"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":0.9200000166893005,"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/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.014700000174343586,"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":0.007899999618530273,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5446000099182129},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5224000215530396},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.47609999775886536},{"id":"https://openalex.org/keywords/plug-in","display_name":"Plug-in","score":0.4332999885082245},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.3865000009536743},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.3686999976634979},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.35269999504089355},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.335099995136261},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3336000144481659}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293999791145325},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5446000099182129},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44600000977516174},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41690000891685486},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.13119","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13119","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.13119","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13119","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.7484508156776428,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spatio-Temporal":[0],"forecasting":[1,163],"is":[2,95],"crucial":[3],"in":[4,47],"diverse":[5],"fields,":[6],"such":[7,38],"as":[8],"transportation,":[9],"climate,":[10],"and":[11,26,60,124,185,193,208],"energy.":[12],"Urban":[13],"spatio-temporal":[14,30],"data":[15],"exhibits":[16],"temporal":[17,83,107],"mirage:":[18],"similar":[19],"short-window":[20,49],"inputs":[21,50],"have":[22,52],"divergent":[23],"future":[24],"trends,":[25],"vice":[27],"versa.":[28],"Existing":[29],"graph":[31],"neural":[32],"networks":[33],"(STGNNs)":[34],"cannot":[35],"effectively":[36],"identify":[37,113],"mirages.":[39,84],"We":[40],"argue":[41],"that":[42,51],"the":[43,48,181,205,209],"core":[44,88],"reason":[45],"lies":[46],"incomplete":[53],"period":[54,148],"observation,":[55],"heterogeneous":[56,131],"global":[57,126,132],"spatial":[58,118,133],"correlation,":[59],"cross-period":[61],"superposition":[62],"causality.":[63],"To":[64],"bridge":[65],"this":[66],"gap,":[67],"we":[68],"develop":[69],"a":[70,77,121,125,140,176],"novel":[71],"Multi-":[72],"Period":[73],"Pattern":[74],"Pre-training":[75],"(MP3),":[76],"plug-and-play":[78],"pre-training":[79],"plugin":[80,152],"for":[81],"distinguishing":[82],"MP3":[85,203],"presents":[86],"two":[87],"innovations:":[89],"(1)":[90],"The":[91,165,212],"multi-period":[92,99,106,115],"pattern":[93,137],"learning":[94],"designed":[96],"to":[97,112,129,143,160],"learn":[98],"patterns":[100],"from":[101],"long":[102],"time":[103],"series.":[104],"Specifically,":[105],"modeling":[108,119],"leverages":[109],"edge":[110],"convolution":[111],"different":[114,147],"patterns.":[116,149],"Multi-period":[117],"uses":[120],"bottleneck":[122],"project":[123],"memory":[127],"bank":[128],"capture":[130,144],"relations":[134],"efficiently.":[135],"Cross-period":[136],"interaction":[138],"employs":[139],"causality-enhanced":[141],"Transformer":[142],"dependencies":[145],"across":[146,171,197],"(2)":[150],"This":[151],"can":[153,214],"seamlessly":[154],"integrate":[155],"into":[156],"existing":[157],"STGNN":[158,169],"backbones":[159],"strengthen":[161],"their":[162],"performance.":[164],"experiment":[166],"on":[167],"five":[168,172],"baselines":[170],"real-world":[173],"datasets":[174],"(including":[175],"large-scale":[177],"dataset":[178],"CA)":[179],"verify":[180],"effectiveness,":[182],"superior":[183],"scalability":[184],"strong":[186],"adaptability":[187],"of":[188],"MP3,":[189],"which":[190],"brings":[191],"consistent":[192],"robust":[194],"performance":[195],"improvements":[196],"all":[198],"evaluated":[199],"baselines.":[200],"On":[201],"average,":[202],"reduces":[204],"MAE":[206],"4.7%":[207],"RMSE":[210],"5.0%.":[211],"code":[213],"be":[215],"available":[216],"at":[217],"https://github.com/YAN-outlook/MP3.":[218]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-13T00:00:00"}