{"id":"https://openalex.org/W7128094841","doi":"https://doi.org/10.48550/arxiv.2602.04153","title":"Pruning for Generalization: A Transfer-Oriented Spatiotemporal Graph Framework","display_name":"Pruning for Generalization: A Transfer-Oriented Spatiotemporal Graph Framework","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7128094841","doi":"https://doi.org/10.48550/arxiv.2602.04153"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.04153","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.04153","pdf_url":"https://arxiv.org/pdf/2602.04153","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2602.04153","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101353825","display_name":"Zihao Jing","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Zihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125147724","display_name":"Yuxi Long","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Yuxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087459414","display_name":"Ganlin Feng","orcid":"https://orcid.org/0009-0009-5360-2578","observed_orcids":["https://orcid.org/0009-0009-5360-2578"]},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Feng, Ganlin","raw_affiliation_strings":["Department of Computer Science Western University London , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Western University London , Canada","institution_ids":["https://openalex.org/I125749732"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/graph-pruning","display_name":"graph pruning","score":0.5410000085830688},{"id":"https://openalex.org/keywords/spatiotemporal-graph-neural-networks","display_name":"spatio-temporal graph neural networks","score":0.878000020980835},{"id":"https://openalex.org/keywords/multivariate-time-series-forecasting","display_name":"multivariate time series forecasting","score":0.984000027179718},{"id":"https://openalex.org/keywords/cross-domain-transfer-learning","display_name":"cross-domain transfer learning","score":0.7160000205039978},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.9520000219345093},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.5529999732971191},{"id":"https://openalex.org/keywords/subgraph-selection","display_name":"subgraph selection","score":0.7139999866485596},{"id":"https://openalex.org/keywords/information-theoretic-criteria","display_name":"information-theoretic criteria","score":0.8330000042915344},{"id":"https://openalex.org/keywords/correlation-based-feature-selection","display_name":"correlation-based feature selection","score":0.8939999938011169},{"id":"https://openalex.org/keywords/traffic-forecasting","display_name":"traffic prediction","score":0.6389999985694885},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.7630000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027000188827515},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6033999919891357},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5929999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587999820709229},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.5432000160217285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5077000260353088},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5056999921798706},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.04153","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.04153","pdf_url":"https://arxiv.org/pdf/2602.04153","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.04153","doi":"https://doi.org/10.48550/arxiv.2602.04153","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.04153","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.04153","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.04153","pdf_url":"https://arxiv.org/pdf/2602.04153","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128094841.pdf","grobid_xml":"https://content.openalex.org/works/W7128094841.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385568303","https://openalex.org/W4410000471","https://openalex.org/W4398229945","https://openalex.org/W7196946295","https://openalex.org/W4406785293","https://openalex.org/W7147833933","https://openalex.org/W4405237283","https://openalex.org/W7125686004","https://openalex.org/W4407631724","https://openalex.org/W7127436244"],"abstract_inverted_index":{"Multivariate":[0],"time":[1],"series":[2],"forecasting":[3,130],"in":[4,74,107],"graph-structured":[5],"domains":[6],"is":[7,83],"critical":[8],"for":[9,124],"real-world":[10],"applications,":[11],"yet":[12],"existing":[13],"spatiotemporal":[14,43,88],"models":[15],"often":[16],"suffer":[17],"from":[18],"performance":[19],"degradation":[20],"under":[21],"data":[22],"scarcity":[23],"and":[24,49,63,71],"cross-domain":[25],"shifts.":[26],"We":[27,38],"address":[28],"these":[29],"challenges":[30],"through":[31],"the":[32,126],"lens":[33],"of":[34,128],"structure-aware":[35],"context":[36,82,116],"selection.":[37],"propose":[39],"TL-GPSTGN,":[40],"a":[41,75,87,120],"transfer-oriented":[42],"framework":[44],"that":[45,102,114],"enhances":[46],"sample":[47],"efficiency":[48],"out-of-distribution":[50],"generalization":[51],"by":[52],"selectively":[53],"pruning":[54,117],"non-optimized":[55],"graph":[56],"context.":[57],"Specifically,":[58],"our":[59],"method":[60],"employs":[61],"information-theoretic":[62],"correlation-based":[64],"criteria":[65],"to":[66,91],"extract":[67],"structurally":[68],"informative":[69],"subgraphs":[70],"features,":[72],"resulting":[73],"compact,":[76],"semantically":[77],"grounded":[78],"representation.":[79],"This":[80],"optimized":[81],"subsequently":[84],"integrated":[85],"into":[86],"convolutional":[89],"architecture":[90],"capture":[92],"complex":[93],"multivariate":[94],"dynamics.":[95],"Evaluations":[96],"on":[97],"large-scale":[98],"traffic":[99],"benchmarks":[100],"demonstrate":[101],"TL-GPSTGN":[103],"consistently":[104],"outperforms":[105],"baselines":[106],"low-data":[108],"transfer":[109],"scenarios.":[110],"Our":[111],"findings":[112],"suggest":[113],"explicit":[115],"serves":[118],"as":[119],"powerful":[121],"inductive":[122],"bias":[123],"improving":[125],"robustness":[127],"graph-based":[129],"models.":[131]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-07T00:00:00"}