{"id":"https://openalex.org/W4404482532","doi":"https://doi.org/10.1109/norcas64408.2024.10752489","title":"Joint CPU-FPGA Hardware-Aware Quantized Training of Graph Convolutional Networks","display_name":"Joint CPU-FPGA Hardware-Aware Quantized Training of Graph Convolutional Networks","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4404482532","doi":"https://doi.org/10.1109/norcas64408.2024.10752489"},"language":"en","primary_location":{"id":"doi:10.1109/norcas64408.2024.10752489","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/norcas64408.2024.10752489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Nordic Circuits and Systems Conference (NorCAS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://liu.diva-portal.org/smash/get/diva2:1952901/FULLTEXT01","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031067990","display_name":"Olle Hansson","orcid":"https://orcid.org/0000-0001-5326-4999"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Olle Hansson","raw_affiliation_strings":["Linköping University,Department of Electrical Engineering,Linköping,Sweden"],"affiliations":[{"raw_affiliation_string":"Linköping University,Department of Electrical Engineering,Linköping,Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028423819","display_name":"Oscar Gustafsson","orcid":"https://orcid.org/0000-0003-3470-3911"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Oscar Gustafsson","raw_affiliation_strings":["Linköping University,Department of Electrical Engineering,Linköping,Sweden"],"affiliations":[{"raw_affiliation_string":"Linköping University,Department of Electrical Engineering,Linköping,Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005255540","display_name":"Jose Nunez\u2010Yanez","orcid":"https://orcid.org/0000-0002-5153-5481"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jose Nunez-Yanez","raw_affiliation_strings":["Linköping University,Department of Electrical Engineering,Linköping,Sweden"],"affiliations":[{"raw_affiliation_string":"Linköping University,Department of Electrical Engineering,Linköping,Sweden","institution_ids":["https://openalex.org/I102134673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031067990"],"corresponding_institution_ids":["https://openalex.org/I102134673"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1872396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9728000164031982,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9728000164031982,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9106000065803528,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7792209386825562},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7592484354972839},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.64467853307724},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5037216544151306},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45444828271865845},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.43911731243133545},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38020798563957214},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32602643966674805},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17871278524398804},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0843559205532074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792209386825562},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7592484354972839},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.64467853307724},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5037216544151306},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45444828271865845},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.43911731243133545},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38020798563957214},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32602643966674805},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17871278524398804},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0843559205532074},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/norcas64408.2024.10752489","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/norcas64408.2024.10752489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Nordic Circuits and Systems Conference (NorCAS)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:liu-213068","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-213068","pdf_url":"https://liu.diva-portal.org/smash/get/diva2:1952901/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:liu-213068","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-213068","pdf_url":"https://liu.diva-portal.org/smash/get/diva2:1952901/FULLTEXT01","source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404482532.pdf","grobid_xml":"https://content.openalex.org/works/W4404482532.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2355315220","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W2316202402","https://openalex.org/W2074043759","https://openalex.org/W2082487009","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506"],"abstract_inverted_index":{"In":[0],"this":[1,110],"work,":[2],"a":[3,31,52,60,78,142],"method":[4],"for":[5,16,109],"training":[6,107,172],"Graph":[7],"Convolutional":[8],"Networks":[9],"where":[10],"the":[11,14,18,41,104,133,151,155,158,176],"bulk":[12],"of":[13,44,63],"computations":[15],"both":[17],"forward":[19],"and":[20,66,73,85,97,170,173],"backward":[21],"passes":[22],"are":[23,75],"performed":[24],"with":[25,51,59,117],"short":[26],"word-length":[27],"fixed-point":[28,130],"operands":[29],"on":[30,154],"unified":[32],"FPGA":[33,49],"hardware":[34,64],"accelerator":[35,39],"is":[36,90],"presented.":[37],"The":[38,71,163],"targets":[40],"programmable":[42],"logic":[43],"an":[45],"AMD":[46],"Zynq":[47],"Utrascale+":[48],"device":[50],"scalable":[53],"architecture":[54,80],"that":[55,102],"can":[56,113],"be":[57],"configured":[58],"variable":[61],"number":[62],"threads":[65],"compute":[67],"units":[68],"per":[69],"thread.":[70],"gradients":[72],"activations":[74],"computed":[76],"using":[77,103],"streaming":[79],"to":[81,92,119,127,132,145,149],"reduce":[82],"memory":[83],"accesses":[84],"pipeline":[86],"stalls":[87],"while":[88],"quantization":[89],"applied":[91],"all":[93],"adjacency,":[94],"feature,":[95],"weight,":[96],"gradient":[98],"tensors.":[99],"Experiments":[100],"show":[101],"hardware-aware":[105],"quantized":[106],"methodology":[108],"application,":[111],"we":[112,140],"achieve":[114],"classification":[115,121],"accuracy":[116,122],"little":[118],"no":[120],"degradation":[123],"when":[124],"quantizing":[125],"down":[126],"4":[128],"-bit":[129,136],"compared":[131,148],"reference":[134],"32":[135],"floating-point":[137],"model.":[138],"Additionally,":[139],"see":[141],"significant,":[143],"up":[144],"34x":[146],"speedup,":[147],"running":[150],"same":[152],"model":[153],"CPU":[156],"in":[157],"processing":[159],"system":[160],"(PS)":[161],"only.":[162],"proposed":[164],"hardware-software":[165],"combination":[166],"enables":[167],"efficient,":[168],"accurate,":[169],"fast":[171],"inference":[174],"at":[175],"edge.":[177]},"counts_by_year":[],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}