{"id":"https://openalex.org/W3127786998","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533623","title":"Intragroup sparsity for efficient inference","display_name":"Intragroup sparsity for efficient inference","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3127786998","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533623","mag":"3127786998"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5071934241","display_name":"Zilin Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zilin Yu","raw_affiliation_strings":["Hangzhou Dianzi University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, HangZhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406898","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0001-7928-2634"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Peking University, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University, ShenZhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710332","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-6500-0445"},"institutions":[{"id":"https://openalex.org/I4401726927","display_name":"Cerebras Systems (United States)","ror":"https://ror.org/040zz8080","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726927"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Cerebras Systems, San Diego, CA, USA"],"affiliations":[{"raw_affiliation_string":"Cerebras Systems, San Diego, CA, USA","institution_ids":["https://openalex.org/I4401726927"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702071","display_name":"Yong Zhao","orcid":"https://orcid.org/0000-0003-2644-952X"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Zhao","raw_affiliation_strings":["Peking University, ShenZhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University, ShenZhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012634258","display_name":"Xundong Wu","orcid":"https://orcid.org/0000-0002-6643-4384"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xundong Wu","raw_affiliation_strings":["Hangzhou Dianzi University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, HangZhou, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071934241"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02322292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9939000010490417,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9847000241279602,"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/dataflow","display_name":"Dataflow","score":0.8715566992759705},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.834295928478241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.753709077835083},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.7049412727355957},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.6310569047927856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3868917226791382},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38358473777770996},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3711201548576355},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36462557315826416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3568902313709259},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1999582052230835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16052287817001343}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8715566992759705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.834295928478241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753709077835083},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.7049412727355957},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.6310569047927856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3868917226791382},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38358473777770996},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3711201548576355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36462557315826416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3568902313709259},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1999582052230835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16052287817001343},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8115881390","display_name":null,"funder_award_id":"62076084","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1667652561","https://openalex.org/W1972501001","https://openalex.org/W2095705004","https://openalex.org/W2117539524","https://openalex.org/W2144567071","https://openalex.org/W2194775991","https://openalex.org/W2285660444","https://openalex.org/W2518108298","https://openalex.org/W2565851976","https://openalex.org/W2604998962","https://openalex.org/W2612445135","https://openalex.org/W2619096655","https://openalex.org/W2625457103","https://openalex.org/W2764043458","https://openalex.org/W2804452021","https://openalex.org/W2808133870","https://openalex.org/W2808168148","https://openalex.org/W2883780447","https://openalex.org/W2889686528","https://openalex.org/W2890947558","https://openalex.org/W2891179104","https://openalex.org/W2895561155","https://openalex.org/W2899244816","https://openalex.org/W2904902077","https://openalex.org/W2907886210","https://openalex.org/W2915106038","https://openalex.org/W2949413532","https://openalex.org/W2950025781","https://openalex.org/W2954580493","https://openalex.org/W2962734576","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963163009","https://openalex.org/W2963263347","https://openalex.org/W2963674932","https://openalex.org/W2963993763","https://openalex.org/W2964169985","https://openalex.org/W2981526169","https://openalex.org/W3012561096","https://openalex.org/W3101584733","https://openalex.org/W3118608800","https://openalex.org/W4240168186","https://openalex.org/W4297775537","https://openalex.org/W4302296459","https://openalex.org/W6637151318","https://openalex.org/W6674330103","https://openalex.org/W6681129735","https://openalex.org/W6725543821","https://openalex.org/W6726275242","https://openalex.org/W6726497184","https://openalex.org/W6737664043","https://openalex.org/W6738642365","https://openalex.org/W6745148473","https://openalex.org/W6746586578","https://openalex.org/W6747633754","https://openalex.org/W6754585794","https://openalex.org/W6754656709","https://openalex.org/W6755120062","https://openalex.org/W6757914502","https://openalex.org/W6765129128","https://openalex.org/W6769520951"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2907307640"],"abstract_inverted_index":{"This":[0],"work":[1],"studies":[2],"intragroup":[3,70,107],"sparsity,":[4],"a":[5,90],"fine-grained":[6,19],"structural":[7],"constraint":[8],"on":[9,38,47,84],"network":[10],"weight":[11,40],"parameters.":[12],"It":[13],"eliminates":[14],"the":[15,27,49,74,101,106],"computational":[16],"inefficiency":[17],"of":[18,51,64,76,97],"sparsity":[20,56,71,108],"due":[21],"to":[22],"irregular":[23],"dataflow,":[24],"while":[25],"at":[26],"same":[28],"time":[29],"achieving":[30,69],"high":[31],"inference":[32],"accuracy.":[33],"We":[34],"present":[35,89],"theoretical":[36],"analysis":[37],"how":[39,48,73],"group":[41],"sizes":[42],"affect":[43,78],"sparsification":[44],"error,":[45],"and":[46,72],"performance":[50],"pruned":[52],"networks":[53],"changes":[54],"with":[55],"level.":[57],"Further,":[58],"we":[59,88],"analyze":[60],"inference-time":[61],"I/O":[62,79],"cost":[63,80],"two":[65],"different":[66],"strategies":[67,77],"for":[68],"choice":[75],"under":[81,105],"mild":[82],"assumptions":[83],"accelerator":[85],"architecture.":[86],"Moreover,":[87],"novel":[91],"training":[92,103],"algorithm":[93],"that":[94],"yield":[95],"models":[96],"improved":[98],"accuracies":[99],"over":[100],"standard":[102],"approach":[104],"constraint.":[109]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}