{"id":"https://openalex.org/W4361198556","doi":"https://doi.org/10.1145/3578244.3583735","title":"Predicting Inference Latency of Neural Architectures on Mobile Devices","display_name":"Predicting Inference Latency of Neural Architectures on Mobile Devices","publication_year":2023,"publication_date":"2023-03-29","ids":{"openalex":"https://openalex.org/W4361198556","doi":"https://doi.org/10.1145/3578244.3583735"},"language":"en","primary_location":{"id":"doi:10.1145/3578244.3583735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578244.3583735","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3578244.3583735","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3578244.3583735","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013473165","display_name":"Zhuojin Li","orcid":"https://orcid.org/0000-0002-8308-0231"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhuojin Li","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036380703","display_name":"Marco Paolieri","orcid":"https://orcid.org/0000-0001-5110-203X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Paolieri","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081582862","display_name":"Leana Golubchik","orcid":"https://orcid.org/0000-0001-8353-5040"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leana Golubchik","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013473165"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.3134,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82175298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9955000281333923,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.982699990272522,"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/computer-science","display_name":"Computer science","score":0.8267923593521118},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8251059651374817},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7542270421981812},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.6060868501663208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5416533946990967},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5198584198951721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4695385694503784},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4351118803024292},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.41875261068344116},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41227132081985474},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35715121030807495},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3512095808982849},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1997177004814148},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07676777243614197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267923593521118},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8251059651374817},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7542270421981812},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.6060868501663208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5416533946990967},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5198584198951721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4695385694503784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4351118803024292},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41875261068344116},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41227132081985474},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35715121030807495},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3512095808982849},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1997177004814148},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07676777243614197},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3578244.3583735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578244.3583735","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3578244.3583735","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3578244.3583735","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3578244.3583735","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3578244.3583735","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G1881860044","display_name":null,"funder_award_id":"1763747","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5269767468","display_name":"CSR: Small: Deconstructing Distributed Deep Learning","funder_award_id":"1816887","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G529689006","display_name":null,"funder_award_id":"CNS-1816887","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7728769296","display_name":null,"funder_award_id":"CCF-1763747","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4361198556.pdf","grobid_xml":"https://content.openalex.org/works/W4361198556.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1503398984","https://openalex.org/W1678356000","https://openalex.org/W2135046866","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2607662938","https://openalex.org/W2883780447","https://openalex.org/W2922395136","https://openalex.org/W2931743911","https://openalex.org/W2953264125","https://openalex.org/W2962861284","https://openalex.org/W2963122961","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2963323244","https://openalex.org/W2963973518","https://openalex.org/W2967733054","https://openalex.org/W2970987838","https://openalex.org/W2982083293","https://openalex.org/W2987175876","https://openalex.org/W3014641072","https://openalex.org/W3034429256","https://openalex.org/W3035414587","https://openalex.org/W3082154327","https://openalex.org/W3105696640","https://openalex.org/W3135408567","https://openalex.org/W3139340366","https://openalex.org/W3157708976","https://openalex.org/W3165698711","https://openalex.org/W3174529902","https://openalex.org/W3175607852","https://openalex.org/W3206502478","https://openalex.org/W3209708143","https://openalex.org/W3210705689","https://openalex.org/W3214953945","https://openalex.org/W4206191901","https://openalex.org/W4287715829","https://openalex.org/W6600763685","https://openalex.org/W6786080308"],"related_works":["https://openalex.org/W3034529322","https://openalex.org/W2589019771","https://openalex.org/W2985540061","https://openalex.org/W2128523353","https://openalex.org/W2113597336","https://openalex.org/W1646292588","https://openalex.org/W2139075651","https://openalex.org/W2134920996","https://openalex.org/W2963830067","https://openalex.org/W91363257"],"abstract_inverted_index":{"Due":[0],"to":[1,21],"the":[2,78],"proliferation":[3],"of":[4,36,40,56,67,80,162],"inference":[5,30,34,91],"tasks":[6],"on":[7,90,94,125,154],"mobile":[8,51,84,127],"devices,":[9],"state-of-the-art":[10],"neural":[11,68,81,156],"architectures":[12,42,82,157],"are":[13],"typically":[14],"designed":[15],"using":[16,129,158],"Neural":[17],"Architecture":[18],"Search":[19],"(NAS)":[20],"achieve":[22],"good":[23],"tradeoffs":[24],"between":[25],"machine":[26,62],"learning":[27,63],"accuracy":[28,114],"and":[29,65,83,111,132],"latency.":[31,92],"While":[32],"measuring":[33],"latency":[35,48,109,117],"a":[37],"huge":[38],"set":[39],"candidate":[41],"during":[43],"NAS":[44],"is":[45,53],"not":[46,140],"feasible,":[47],"prediction":[49],"for":[50],"devices":[52,85,128],"challenging,":[54],"because":[55],"hardware":[57],"heterogeneity,":[58],"optimizations":[59],"applied":[60],"by":[61,71,106,121],"frameworks,":[64],"diversity":[66],"architectures.":[69],"Motivated":[70],"these":[72,104],"challenges,":[73],"we":[74,97,145],"first":[75],"quantitatively":[76],"assess":[77],"characteristics":[79],"that":[86,136,148],"have":[87],"significant":[88],"effects":[89],"Based":[93],"this":[95],"assessment,":[96],"propose":[98],"an":[99],"operation-wise":[100,108],"framework":[101],"which":[102],"addresses":[103],"challenges":[105],"developing":[107],"predictors":[110],"achieves":[112],"high":[113],"in":[115],"end-to-end":[116],"predictions,":[118],"as":[119],"shown":[120],"our":[122,137],"comprehensive":[123],"evaluations":[124],"multiple":[126],"multicore":[130],"CPUs":[131],"GPUs.":[133],"To":[134],"illustrate":[135],"approach":[138],"does":[139],"require":[141],"expensive":[142],"data":[143],"collection,":[144],"also":[146],"show":[147],"accurate":[149],"predictions":[150],"can":[151],"be":[152],"achieved":[153],"real-world":[155],"only":[159],"small":[160],"amounts":[161],"profiling":[163],"data.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}