{"id":"https://openalex.org/W4386709670","doi":"https://doi.org/10.1145/3605573.3605625","title":"SNICIT: Accelerating Sparse Neural Network Inference via Compression at Inference Time on GPU","display_name":"SNICIT: Accelerating Sparse Neural Network Inference via Compression at Inference Time on GPU","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386709670","doi":"https://doi.org/10.1145/3605573.3605625"},"language":"en","primary_location":{"id":"doi:10.1145/3605573.3605625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","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/A5103137666","display_name":"Shui Jiang","orcid":"https://orcid.org/0000-0003-0718-1003"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shui Jiang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088685794","display_name":"Tsung\u2010Wei Huang","orcid":"https://orcid.org/0000-0001-9768-3378"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsung-Wei Huang","raw_affiliation_strings":["The University of Wisconsin at Madison, United States of America"],"affiliations":[{"raw_affiliation_string":"The University of Wisconsin at Madison, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051340429","display_name":"Bei Yu","orcid":"https://orcid.org/0000-0001-6406-4810"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Yu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062800747","display_name":"Tsung-Yi Ho","orcid":"https://orcid.org/0000-0001-7348-5625"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tsung-Yi Ho","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103137666"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":2.8399,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92628481,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8202973008155823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7447366714477539},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4581334888935089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38937872648239136}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8202973008155823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447366714477539},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4581334888935089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38937872648239136}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605573.3605625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G471277597","display_name":null,"funder_award_id":"CCF-2126672, CCF-2144523 (CAREER), OAC-2209957, and TI-2229304","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2019397928","https://openalex.org/W2164500538","https://openalex.org/W2963366311","https://openalex.org/W2971115712","https://openalex.org/W2972437276","https://openalex.org/W2990185852","https://openalex.org/W2990514424","https://openalex.org/W3006363700","https://openalex.org/W3081515890","https://openalex.org/W3100809954","https://openalex.org/W3100839241","https://openalex.org/W3113443077","https://openalex.org/W3130660608","https://openalex.org/W3159624436","https://openalex.org/W3188917597","https://openalex.org/W3199463158","https://openalex.org/W3208113647","https://openalex.org/W4200090124","https://openalex.org/W4200369086","https://openalex.org/W4205834599","https://openalex.org/W4226437492","https://openalex.org/W4283389995","https://openalex.org/W4287123848","https://openalex.org/W4292779060","https://openalex.org/W4308090217","https://openalex.org/W4308090748","https://openalex.org/W6770156499","https://openalex.org/W6778883912","https://openalex.org/W6785208269","https://openalex.org/W6785386067"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Sparse":[0],"deep":[1],"neural":[2],"network":[3],"(DNN)":[4],"has":[5],"become":[6],"an":[7],"important":[8],"technique":[9],"for":[10,51],"reducing":[11],"the":[12,41,56,60,155],"inference":[13,27,49,82,105,109,128],"cost":[14],"of":[15],"large":[16,20,52,102],"DNNs.":[17,54],"However,":[18],"computing":[19],"sparse":[21,53,73,103],"DNNs":[22,139],"is":[23],"very":[24],"challenging":[25],"because":[26],"iterations":[28],"can":[29,85],"incur":[30],"highly":[31],"irregular":[32],"patterns":[33],"and":[34,137,148],"unbalanced":[35],"loads.":[36],"To":[37],"address":[38],"this":[39],"challenge,":[40],"recent":[42],"HPEC":[43,133],"Graph":[44,134],"Challenge":[45,135],"seeks":[46],"novel":[47],"high-performance":[48],"methods":[50],"Despite":[55],"rapid":[57],"progress":[58],"over":[59,127,154],"past":[61],"four":[62],"years,":[63],"solutions":[64],"have":[65],"largely":[66,124],"focused":[67],"on":[68,131],"static":[69],"model":[70],"compression":[71,80,107],"or":[72],"multiplication":[74],"kernels,":[75],"while":[76],"ignoring":[77],"dynamic":[78],"data":[79,113],"at":[81,108],"time":[83],"which":[84],"achieve":[86],"significant":[87],"yet":[88],"untapped":[89],"performance":[90],"benefits.":[91],"Consequently,":[92],"we":[93],"propose":[94],"SNICIT,":[95],"a":[96,120],"new":[97],"GPU":[98],"algorithm":[99],"to":[100,115],"accelerate":[101],"DNN":[104],"via":[106],"time.":[110],"SNICIT":[111,142],"leverages":[112],"clustering":[114],"transform":[116],"intermediate":[117],"results":[118],"into":[119],"sparser":[121],"representation":[122],"that":[123],"reduces":[125],"computation":[126],"iterations.":[129],"Evaluated":[130],"both":[132],"benchmarks":[136],"conventional":[138],"(MNIST,":[140],"CIFAR-10),":[141],"achieves":[143],"6":[144],"\u223c":[145,150],"444":[146],"\u00d7":[147,152],"1.36":[149],"1.95":[151],"speed-ups":[153],"previous":[156],"champions,":[157],"respectively.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}