{"id":"https://openalex.org/W4205706318","doi":"https://doi.org/10.23919/eusipco54536.2021.9616314","title":"Recurrent Graph Tensor Networks: A Low-Complexity Framework for Modelling High-Dimensional Multi-Way Sequences","display_name":"Recurrent Graph Tensor Networks: A Low-Complexity Framework for Modelling High-Dimensional Multi-Way Sequences","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4205706318","doi":"https://doi.org/10.23919/eusipco54536.2021.9616314"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616314","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616314","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5053802268","display_name":"Yao Xu","orcid":"https://orcid.org/0000-0003-3315-2070"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yao Lei Xu","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,London,United Kingdom","Department of Electrical and Electronic Engineering, Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,London,United Kingdom","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103001848","display_name":"Danilo P. Mandic","orcid":"https://orcid.org/0000-0001-8432-3963"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Danilo P. Mandic","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,London,United Kingdom","Department of Electrical and Electronic Engineering, Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,London,United Kingdom","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053802268"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.3158,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.46153846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1795","last_page":"1799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9854999780654907,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7285522222518921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.702172577381134},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.6012716889381409},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.587695837020874},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.524944543838501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49822044372558594},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45731067657470703},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3434232473373413},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2889406085014343},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18244203925132751}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7285522222518921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.702172577381134},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6012716889381409},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.587695837020874},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.524944543838501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49822044372558594},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45731067657470703},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434232473373413},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2889406085014343},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18244203925132751},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616314","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616314","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1798945469","https://openalex.org/W1825959699","https://openalex.org/W1852909287","https://openalex.org/W1993482030","https://openalex.org/W1995406764","https://openalex.org/W1996869553","https://openalex.org/W2299597119","https://openalex.org/W2311161367","https://openalex.org/W2489292218","https://openalex.org/W2516041031","https://openalex.org/W2558748708","https://openalex.org/W2617994470","https://openalex.org/W2754880706","https://openalex.org/W2765932895","https://openalex.org/W2963704562","https://openalex.org/W2997209505","https://openalex.org/W3107718410","https://openalex.org/W3107724517","https://openalex.org/W3108029334","https://openalex.org/W4210257598","https://openalex.org/W6638060716","https://openalex.org/W6638868411","https://openalex.org/W6638909124","https://openalex.org/W6741042017","https://openalex.org/W6745544366","https://openalex.org/W6771915822","https://openalex.org/W6807384801"],"related_works":["https://openalex.org/W2922457425","https://openalex.org/W4250304930","https://openalex.org/W4213142596","https://openalex.org/W4281386417","https://openalex.org/W2793022090","https://openalex.org/W4327831767","https://openalex.org/W4298168912","https://openalex.org/W4327531511","https://openalex.org/W4366674482","https://openalex.org/W2919358988"],"abstract_inverted_index":{"Recurrent":[0,73],"Neural":[1],"Networks":[2],"(RNNs)":[3],"are":[4],"among":[5],"the":[6,24,46,97,106,115,129],"most":[7],"successful":[8],"machine":[9],"learning":[10],"models":[11],"for":[12,44],"sequence":[13,86],"modelling,":[14],"but":[15,126],"tend":[16],"to":[17,61],"suffer":[18],"from":[19],"an":[20],"exponential":[21],"increase":[22],"in":[23,51,56,70,140],"number":[25],"of":[26,48,96,102,109,120,131,142],"parameters":[27],"when":[28],"dealing":[29],"with":[30,134],"large":[31],"multidimensional":[32],"data.":[33],"To":[34],"this":[35],"end,":[36],"we":[37,112],"develop":[38],"a":[39,57,71],"multi-linear":[40],"graph":[41,103],"filter":[42],"framework":[43,80],"approximating":[45],"modelling":[47,63,87],"hidden":[49],"states":[50],"RNNs,":[52,125,136],"which":[53],"is":[54,81,118],"embedded":[55],"tensor":[58,110],"network":[59],"architecture":[60],"improve":[62],"power":[64,108],"and":[65,89,105,144],"reduce":[66],"parameter":[67],"complexity,":[68],"resulting":[69],"novel":[72],"Graph":[74],"Tensor":[75],"Network":[76],"(RGTN).":[77],"The":[78],"proposed":[79,116],"validated":[82],"through":[83],"several":[84],"multi-way":[85],"tasks":[88],"benchmarked":[90],"against":[91],"traditional":[92,135],"RNNs.":[93],"By":[94],"virtue":[95],"domain":[98],"aware":[99],"information":[100],"processing":[101],"filters":[104],"expressive":[107],"networks,":[111],"show":[113],"that":[114],"RGTN":[117],"capable":[119],"not":[121],"only":[122],"outperforming":[123],"standard":[124],"also":[127],"mitigating":[128],"Curse":[130],"Dimensionality":[132],"associated":[133],"demonstrating":[137],"superior":[138],"properties":[139],"terms":[141],"performance":[143],"complexity.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}