{"id":"https://openalex.org/W4385681602","doi":"https://doi.org/10.48550/arxiv.2308.03210","title":"Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series","display_name":"Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series","publication_year":2023,"publication_date":"2023-08-06","ids":{"openalex":"https://openalex.org/W4385681602","doi":"https://doi.org/10.48550/arxiv.2308.03210"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2308.03210","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.03210","pdf_url":"https://arxiv.org/pdf/2308.03210","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/2308.03210","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013281995","display_name":"Chrysoula Kosma","orcid":"https://orcid.org/0000-0003-4255-4485","observed_orcids":["https://orcid.org/0000-0003-4255-4485"]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Kosma, Chrysoula","raw_affiliation_strings":["\u00c9cole Polytechnique , IP Paris France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique , IP Paris France","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011742954","display_name":"Giannis Nikolentzos","orcid":"https://orcid.org/0000-0002-0336-5879","observed_orcids":["https://orcid.org/0000-0002-0336-5879"]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nikolentzos, Giannis","raw_affiliation_strings":["\u00c9cole Polytechnique , IP Paris France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique , IP Paris France","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057695979","display_name":"Michalis Vazirgiannis","orcid":"https://orcid.org/0000-0001-5923-4440","observed_orcids":["https://orcid.org/0000-0001-5923-4440"]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vazirgiannis, Michalis","raw_affiliation_strings":["\u00c9cole Polytechnique , IP Paris France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique , IP Paris France","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}]}],"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":12,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.0008999999845400453,"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/T11210","display_name":"Mathematical Analysis and Transform Methods","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2604","display_name":"Applied Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/irregularly-sampled-time-series","display_name":"irregularly sampled time series","score":0.9909999966621399},{"id":"https://openalex.org/keywords/multivariate-time-series","display_name":"multivariate time series","score":0.9700000286102295},{"id":"https://openalex.org/keywords/irregular-time-intervals","display_name":"irregular time intervals","score":0.5920000076293945},{"id":"https://openalex.org/keywords/time-series-interpolation","display_name":"time series interpolation","score":0.8320000171661377},{"id":"https://openalex.org/keywords/time-series-classification","display_name":"time series classification","score":0.9710000157356262},{"id":"https://openalex.org/keywords/sparse-observations","display_name":"sparse observations","score":0.3970000147819519}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8234910368919373},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.774527907371521},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7388794422149658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103381752967834},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.65232253074646},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6134403347969055},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5696766376495361},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5132057666778564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4975169003009796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4717871844768524},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4692131578922272},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.45279228687286377},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.448012113571167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43814489245414734},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3898164629936218},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32868534326553345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1802203357219696},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2308.03210","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.03210","pdf_url":"https://arxiv.org/pdf/2308.03210","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.2308.03210","doi":"https://doi.org/10.48550/arxiv.2308.03210","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.03210","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:2308.03210","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.03210","pdf_url":"https://arxiv.org/pdf/2308.03210","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385681602.pdf","grobid_xml":"https://content.openalex.org/works/W4385681602.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W2622068151","https://openalex.org/W2761228892","https://openalex.org/W2913870675","https://openalex.org/W3043567704","https://openalex.org/W3128694157"],"related_works":["https://openalex.org/W4385279077","https://openalex.org/W4386795761","https://openalex.org/W3034473101","https://openalex.org/W2913870675","https://openalex.org/W3210522174","https://openalex.org/W4382284852","https://openalex.org/W4286632719","https://openalex.org/W7140162748","https://openalex.org/W3209661192","https://openalex.org/W7167854887"],"abstract_inverted_index":{"Irregularly":[0],"sampled":[1,135,150],"multivariate":[2,151],"time":[3,49,64,95,136,152,197],"series":[4,50,153,190],"are":[5],"ubiquitous":[6],"in":[7,74,204,214],"several":[8],"application":[9,211],"domains,":[10],"leading":[11],"to":[12,47,61],"sparse,":[13],"not":[14,70],"fully-observed":[15],"and":[16,33,104,144,207],"non-aligned":[17],"observations":[18],"across":[19],"different":[20],"variables.":[21],"Standard":[22],"sequential":[23],"neural":[24,30,35,67,119],"network":[25,120,202],"architectures,":[26],"such":[27],"as":[28],"recurrent":[29],"networks":[31,36,68],"(RNNs)":[32],"convolutional":[34,66,84,110,118],"(CNNs),":[37],"consider":[38],"regular":[39],"spacing":[40],"between":[41],"observation":[42],"times,":[43],"posing":[44],"significant":[45],"challenges":[46],"irregular":[48,63,76],"modeling.":[51],"While":[52],"most":[53],"of":[54,94,100,162,187,195,212],"the":[55,75,97,116,159,163,178,181,185,188,193,201,209],"proposed":[56,164,182],"architectures":[57],"incorporate":[58],"RNN":[59],"variants":[60],"handle":[62],"intervals,":[65],"have":[69],"been":[71],"adequately":[72],"studied":[73],"sampling":[77],"setting.":[78],"In":[79],"this":[80,215],"paper,":[81],"we":[82],"parameterize":[83],"layers":[85],"by":[86,191],"employing":[87],"time-explicitly":[88],"initialized":[89],"kernels.":[90],"Such":[91],"general":[92],"functions":[93,198],"enhance":[96],"learning":[98],"process":[99],"continuous-time":[101],"hidden":[102],"dynamics":[103],"can":[105],"be":[106],"efficiently":[107],"incorporated":[108],"into":[109],"kernel":[111],"weights.":[112],"We,":[113],"thus,":[114],"propose":[115],"time-parameterized":[117],"(TPCNN),":[121],"which":[122,167],"shares":[123],"similar":[124],"properties":[125],"with":[126],"vanilla":[127],"convolutions":[128,213],"but":[129],"is":[130,168],"carefully":[131],"designed":[132],"for":[133],"irregularly":[134,149],"series.":[137],"We":[138],"evaluate":[139],"TPCNN":[140,165],"on":[141],"both":[142],"interpolation":[143],"classification":[145],"tasks":[146,206],"involving":[147],"real-world":[148],"datasets.":[154],"Our":[155],"experimental":[156],"results":[157],"indicate":[158],"competitive":[160],"performance":[161,203],"model":[166],"also":[169],"significantly":[170],"more":[171],"efficient":[172],"than":[173],"other":[174],"state-of-the-art":[175],"methods.":[176],"At":[177],"same":[179],"time,":[180],"architecture":[183],"allows":[184],"interpretability":[186],"input":[189],"leveraging":[192],"combination":[194],"learnable":[196],"that":[199],"improve":[200],"subsequent":[205],"expedite":[208],"inaugural":[210],"field.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2023-08-09T00:00:00"}