{"id":"https://openalex.org/W4416017876","doi":"https://doi.org/10.1145/3746252.3761432","title":"Decoder-only Pre-training Enhancement for Spatio-temporal Traffic Forecasting","display_name":"Decoder-only Pre-training Enhancement for Spatio-temporal Traffic Forecasting","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017876","doi":"https://doi.org/10.1145/3746252.3761432"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761432","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101653548","display_name":"T.L. Yu","orcid":"https://orcid.org/0000-0001-8349-9131"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tao Yu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021400908","display_name":"Junhong Wan","orcid":"https://orcid.org/0000-0003-3366-0016"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhong Wan","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091640552","display_name":"Yao Fu","orcid":"https://orcid.org/0000-0002-8931-3665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Fu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082728339","display_name":"Weihao Jiang","orcid":"https://orcid.org/0000-0003-3482-8538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihao Jiang","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101210862","display_name":"Jiang Zhu","orcid":"https://orcid.org/0009-0006-0877-0490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang Zhu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101653548"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37778538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3942","last_page":"3951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9763000011444092,"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":0.9763000011444092,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0035000001080334187,"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/T10524","display_name":"Traffic control and management","score":0.0019000000320374966,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5389000177383423},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4489000141620636},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4293999969959259},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.3880000114440918},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3653999865055084},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3596000075340271},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3237999975681305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858999967575073},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4187999963760376},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3596000075340271},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32510000467300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32409998774528503},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3095000088214874},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.288100004196167},{"id":"https://openalex.org/C2993660032","wikidata":"https://www.wikidata.org/wiki/Q746984","display_name":"Traffic speed","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C2985695025","wikidata":"https://www.wikidata.org/wiki/Q4323994","display_name":"Road traffic","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C11940443","wikidata":"https://www.wikidata.org/wiki/Q16965645","display_name":"Slowness","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761432","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1562396680","https://openalex.org/W1983883318","https://openalex.org/W2106822551","https://openalex.org/W2903871660","https://openalex.org/W2907492528","https://openalex.org/W2996847713","https://openalex.org/W3123909522","https://openalex.org/W3125675327","https://openalex.org/W3217450528","https://openalex.org/W4295857769","https://openalex.org/W4382239616","https://openalex.org/W4382449675","https://openalex.org/W4388936714","https://openalex.org/W4403600951"],"related_works":[],"abstract_inverted_index":{"Although":[0],"spatio-temporal":[1],"graph":[2],"neural":[3],"networks":[4],"(STGNNs)":[5],"become":[6],"widely":[7],"used":[8],"methods":[9],"in":[10],"traffic":[11,76,93,155,211],"forecasting,":[12,94,105],"they":[13],"still":[14],"encounter":[15],"an":[16],"issue":[17],"named":[18,122],"short-sightedness.":[19],"Specifically,":[20,158],"due":[21],"to":[22,33,47,57,70,78,150,172,184,193],"high":[23],"model":[24,194],"complexity":[25],"and":[26,52,103,126,133,165,189],"GPU":[27],"memory":[28],"usage,":[29],"STGNNs":[30,46,202],"are":[31],"restricted":[32],"processing":[34],"only":[35],"very":[36],"short":[37],"input":[38],"time":[39,60],"series.":[40],"This":[41],"limited":[42],"context":[43],"often":[44],"causes":[45],"focus":[48],"on":[49,75,137],"local":[50],"variations":[51],"overlook":[53],"long-term":[54],"patterns,":[55],"leading":[56],"misinterpretation":[58],"of":[59,154],"series":[61,77],"trends.":[62],"To":[63,112],"tackle":[64],"this":[65,114,138],"issue,":[66],"recent":[67],"studies":[68],"propose":[69,117,178],"perform":[71],"mask":[72,85],"reconstruction":[73,86],"pre-training":[74,90,102,120,156],"enhance":[79],"STGNNs.":[80],"However,":[81],"we":[82,116,140,177,213],"argue":[83],"that":[84],"is":[87],"a":[88,98,118,142,179],"suboptimal":[89],"paradigm":[91,121],"for":[92],"because":[95],"there":[96],"exists":[97],"great":[99],"gap":[100],"between":[101],"downstream":[104],"caused":[106],"by":[107],"their":[108],"inconsistent":[109],"training":[110],"targets.":[111],"eliminate":[113],"gap,":[115],"new":[119,143,180],"next":[123,167],"patch":[124,168],"prediction":[125,169],"prove":[127],"its":[128,215],"advantages":[129],"from":[130],"both":[131],"empirical":[132],"theoretical":[134],"perspectives.":[135],"Based":[136],"paradigm,":[139],"introduce":[141],"framework":[144],"called":[145],"Decoder-only":[146],"Pre-training":[147],"Enhancement":[148],"(DoP)":[149],"unleash":[151],"the":[152],"potential":[153],"model.":[157],"DoP":[159,199],"uses":[160],"Transformer":[161],"decoders":[162],"as":[163,170],"infrastructure,":[164],"leverages":[166],"target":[171],"conduct":[173],"pre-training.":[174],"In":[175],"addition,":[176],"dual-view":[181],"temporal":[182,187],"embedding":[183],"fully":[185],"capture":[186],"information":[188],"spatial":[190,195],"spectral":[191],"enhancement":[192,206],"information.":[196],"After":[197],"pre-training,":[198],"enhances":[200],"existing":[201],"seamlessly":[203],"with":[204],"periodic":[205],"mechanism.":[207],"On":[208],"four":[209],"real-world":[210],"benchmarks,":[212],"demonstrate":[214],"start-of-the-art":[216],"performance.":[217]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-08T00:00:00"}