{"id":"https://openalex.org/W4226439885","doi":"https://doi.org/10.1145/3550075","title":"LW-GCN: A Lightweight FPGA-based Graph Convolutional Network Accelerator","display_name":"LW-GCN: A Lightweight FPGA-based Graph Convolutional Network Accelerator","publication_year":2022,"publication_date":"2022-08-04","ids":{"openalex":"https://openalex.org/W4226439885","doi":"https://doi.org/10.1145/3550075"},"language":"en","primary_location":{"id":"doi:10.1145/3550075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3550075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3550075","source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3550075","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005340074","display_name":"Zhuofu Tao","orcid":"https://orcid.org/0000-0003-0951-1811"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuofu Tao","raw_affiliation_strings":["Electrical and Computer Engineering, University of California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0003-0951-1811","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101491215","display_name":"C.-L. Wu","orcid":"https://orcid.org/0000-0002-9939-8922"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Wu","raw_affiliation_strings":["Electrical and Computer Engineering, University of California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-9939-8922","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390856","display_name":"Yuan Liang","orcid":"https://orcid.org/0000-0002-1861-4479"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Liang","raw_affiliation_strings":["Electrical and Computer Engineering, University of California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-1861-4479","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015932760","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-7288-1789"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["Electrical and Computer Engineering, University of California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-7288-1789","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059721426","display_name":"Lei He","orcid":"https://orcid.org/0000-0002-9698-0319"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Electrical and Computer Engineering, University of California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-9698-0319","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":3.942,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94260297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9987000226974487,"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":0.9987000226974487,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9787999987602234,"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":0.8475219011306763},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7142529487609863},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6467055678367615},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5682904124259949},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5599856972694397},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.543336808681488},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4217623174190521},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41840609908103943},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33192288875579834},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21959608793258667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18248212337493896},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.09381401538848877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8475219011306763},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7142529487609863},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6467055678367615},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5682904124259949},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5599856972694397},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.543336808681488},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4217623174190521},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41840609908103943},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33192288875579834},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21959608793258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18248212337493896},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.09381401538848877},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":1,"locations":[{"id":"doi:10.1145/3550075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3550075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3550075","source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3550075","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3550075","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3550075","source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226439885.pdf","grobid_xml":"https://content.openalex.org/works/W4226439885.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2018569868","https://openalex.org/W2116341502","https://openalex.org/W2141248063","https://openalex.org/W2141861439","https://openalex.org/W2253675773","https://openalex.org/W2285660444","https://openalex.org/W2515287984","https://openalex.org/W2519887557","https://openalex.org/W2559655401","https://openalex.org/W2604314403","https://openalex.org/W2624431344","https://openalex.org/W2766801974","https://openalex.org/W2768308213","https://openalex.org/W2787740662","https://openalex.org/W2807021761","https://openalex.org/W2945827377","https://openalex.org/W2947873642","https://openalex.org/W2948035163","https://openalex.org/W2961295589","https://openalex.org/W2964015378","https://openalex.org/W2971600697","https://openalex.org/W2979455536","https://openalex.org/W3008408165","https://openalex.org/W3017228913","https://openalex.org/W3034371431","https://openalex.org/W3047846843","https://openalex.org/W3089149858","https://openalex.org/W3100848837","https://openalex.org/W3101553402","https://openalex.org/W3105753905","https://openalex.org/W3117528324","https://openalex.org/W3157609068","https://openalex.org/W3167722510","https://openalex.org/W3193327410","https://openalex.org/W4240168186","https://openalex.org/W4293649366","https://openalex.org/W4294554825","https://openalex.org/W4294558607","https://openalex.org/W7038994942"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W4225949190","https://openalex.org/W2518118925","https://openalex.org/W2532502681","https://openalex.org/W3159273459"],"abstract_inverted_index":{"Graph":[0],"convolutional":[1],"networks":[2],"(GCNs)":[3],"have":[4],"been":[5],"introduced":[6],"to":[7,46,68,100,150,163,174],"effectively":[8],"process":[9,67],"non-Euclidean":[10],"graph":[11],"data.":[12],"However,":[13],"GCNs":[14],"incur":[15],"large":[16],"amounts":[17],"of":[18,29,123,196],"irregularity":[19,70],"in":[20,71,76],"computation":[21,72],"and":[22,43,73,90,105,114,117,121,137,154,166,168,177,193,198],"memory":[23,41,74],"access,":[24],"which":[25],"prevents":[26],"efficient":[27],"use":[28],"traditional":[30],"neural":[31],"network":[32],"accelerators.":[33],"Moreover,":[34,109],"existing":[35,151],"dedicated":[36],"GCN":[37,77,83,124,136],"accelerators":[38],"demand":[39],"high":[40],"volumes":[42],"are":[44,139],"difficult":[45],"implement":[47],"onto":[48,126],"resource":[49,131],"limited":[50,132],"edge":[51,185],"devices.":[52],"In":[53],"this":[54],"work,":[55],"we":[56,110],"propose":[57,95],"LW-GCN,":[58],"a":[59,64,96,127],"lightweight":[60],"FPGA-based":[61,156],"accelerator":[62],"with":[63,145,182],"software-hardware":[65],"co-designed":[66],"tackle":[69],"access":[75],"inference.":[78],"LW-GCN":[79,158,190],"decomposes":[80],"the":[81],"main":[82],"operations":[84],"into":[85],"Sparse":[86],"Matrix-Matrix":[87,91],"Multiplication":[88,92],"(SpMM)":[89],"(MM).":[93],"We":[94],"novel":[97],"compression":[98],"format":[99],"balance":[101],"workload":[102,115],"across":[103],"PEs":[104],"prevent":[106],"data":[107,112],"hazards.":[108],"apply":[111],"quantization":[113],"tiling,":[116],"map":[118],"both":[119],"SpMM":[120],"MM":[122],"inference":[125],"uniform":[128],"architecture":[129],"on":[130,135,141],"hardware.":[133],"Evaluation":[134],"GraphSAGE":[138],"performed":[140],"Xilinx":[142],"Kintex-7":[143],"FPGA":[144],"three":[146],"popular":[147],"datasets.":[148],"Compared":[149],"CPU,":[152],"GPU,":[153],"state-of-the-art":[155],"accelerator,":[157],"reduces":[159],"latency":[160],"by":[161,172],"up":[162,173],"60\u00d7,":[164],"12\u00d7,":[165],"1.7\u00d7":[167],"increases":[169],"power":[170],"efficiency":[171],"912\u00d7,":[175],"511\u00d7,":[176],"3.87\u00d7,":[178],"respectively.":[179,200],"Furthermore,":[180],"compared":[181],"NVIDIA\u2019s":[183],"latest":[184],"GPU":[186],"Jetson":[187],"Xavier":[188],"NX,":[189],"achieves":[191],"speedup":[192],"energy":[194],"savings":[195],"32\u00d7":[197],"84\u00d7,":[199]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}