{"id":"https://openalex.org/W4415179253","doi":"https://doi.org/10.1109/tcad.2025.3621532","title":"LEAP: Lightweight Neural Network Inference Through Proactive Early-Exiting Prediction","display_name":"LEAP: Lightweight Neural Network Inference Through Proactive Early-Exiting Prediction","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415179253","doi":"https://doi.org/10.1109/tcad.2025.3621532"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2025.3621532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3621532","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-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/A5079024501","display_name":"Yingtao Shen","orcid":"https://orcid.org/0009-0001-7868-5340"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingtao Shen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0009-0001-7868-5340","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012206667","display_name":"Xiangjie Li","orcid":"https://orcid.org/0000-0002-9600-8984"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangjie Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024303770","display_name":"Yehan Ma","orcid":"https://orcid.org/0000-0002-8595-1619"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yehan Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0002-8595-1619","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062801966","display_name":"Weidong Cao","orcid":"https://orcid.org/0000-0001-7539-8250"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weidong Cao","raw_affiliation_strings":["George Washington University, Washington, DC, USA","George Washington University, USA"],"raw_orcid":"https://orcid.org/0000-0001-7539-8250","affiliations":[{"raw_affiliation_string":"George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"George Washington University, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101758228","display_name":"Jie Zhao","orcid":"https://orcid.org/0000-0002-5191-9637"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Zhao","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090386055","display_name":"An Zou","orcid":"https://orcid.org/0000-0002-0083-5281"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An Zou","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0002-0083-5281","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14436618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"6","first_page":"2799","last_page":"2812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8468999862670898,"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/T10320","display_name":"Neural Networks and Applications","score":0.8468999862670898,"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/computation","display_name":"Computation","score":0.8008000254631042},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.689300000667572},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.6409000158309937},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.618399977684021},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6111999750137329},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5831000208854675},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5375999808311462}],"concepts":[{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.8008000254631042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906000018119812},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.689300000667572},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.618399977684021},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4677000045776367},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42309999465942383},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33869999647140503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C93682380","wikidata":"https://www.wikidata.org/wiki/Q2025226","display_name":"Static timing analysis","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2025.3621532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2025.3621532","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1378043533","display_name":null,"funder_award_id":"62202287","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6076703422","display_name":null,"funder_award_id":"62473254","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7320542902","display_name":null,"funder_award_id":"21CGA11","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7659338309","display_name":null,"funder_award_id":"62103268","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,23,28,91,117],"incorporation":[4],"of":[5],"early":[6,56,105,173],"exit":[7,31,48,57,97,111,174],"layers":[8],"into":[9],"deep":[10],"neural":[11],"networks":[12],"has":[13],"allowed":[14],"inference":[15,71],"to":[16,46,113,134,140,153,161,166,171,179],"terminate":[17],"earlier":[18],"while":[19,51,138,188],"maintaining":[20,189],"accuracy.":[21],"However,":[22],"passive":[24],"decision-making":[25],"involved":[26],"in":[27,168],"these":[29,75],"static":[30],"placement":[32,37,53],"creates":[33],"a":[34,86],"dilemma:":[35],"fine-grained":[36],"may":[38,54],"cause":[39],"high":[40],"performance":[41],"and":[42,77,80,126,163,183,192],"energy":[43,81,136,186],"overhead":[44],"due":[45],"frequent":[47],"layer":[49,112],"execution,":[50],"coarse-grained":[52],"miss":[55],"opportunities.":[58],"Moreover,":[59],"common":[60],"energy-saving":[61],"techniques":[62],"like":[63],"adjusting":[64],"processor":[65,122],"configurations":[66],"are":[67],"not":[68],"applicable":[69],"once":[70],"begins.":[72],"To":[73],"overcome":[74],"challenges":[76],"improve":[78],"computation":[79,102,158,182],"efficiency,":[82],"we":[83],"propose":[84],"LEAP,":[85],"software-hardware":[87],"co-design":[88],"approach.":[89],"On":[90,116],"software":[92],"side,":[93,119],"LEAP":[94,120,148,156,176],"proactively":[95],"predicts":[96],"points":[98],"at":[99],"runtime,":[100],"reducing":[101],"by":[103,159],"enabling":[104],"exits":[106,133],"without":[107],"requiring":[108],"every":[109],"pre-placed":[110],"be":[114],"executed.":[115],"hardware":[118],"adjusts":[121],"settings\u2014such":[123],"as":[124],"frequency":[125],"voltage\u2014based":[127],"on":[128],"single":[129],"or":[130],"multiple":[131],"predicted":[132],"optimize":[135],"consumption":[137],"adhering":[139],"latency":[141],"requirements.":[142],"Extensive":[143],"experimental":[144],"results":[145],"show":[146],"that":[147],"significantly":[149],"improves":[150],"efficiency.":[151],"Compared":[152,170],"standard":[154],"inference,":[155],"reduces":[157],"up":[160,165,178],"76.4%":[162],"saves":[164],"83.2%":[167],"energy.":[169],"state-of-the-art":[172],"methods,":[175],"achieves":[177],"27.9%":[180],"less":[181],"57.1%":[184],"more":[185],"savings,":[187],"similar":[190],"accuracy":[191],"latency.":[193]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-15T00:00:00"}