{"id":"https://openalex.org/W3098718496","doi":"https://doi.org/10.1109/tetc.2020.3037052","title":"Incremental Learning Using a Grow-and-Prune Paradigm With Efficient Neural Networks","display_name":"Incremental Learning Using a Grow-and-Prune Paradigm With Efficient Neural Networks","publication_year":2020,"publication_date":"2020-11-10","ids":{"openalex":"https://openalex.org/W3098718496","doi":"https://doi.org/10.1109/tetc.2020.3037052","mag":"3098718496"},"language":"en","primary_location":{"id":"doi:10.1109/tetc.2020.3037052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2020.3037052","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","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/A5080137972","display_name":"Xiaoliang Dai","orcid":"https://orcid.org/0000-0003-3098-2714"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoliang Dai","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0003-3098-2714","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002444694","display_name":"Hongxu Yin","orcid":"https://orcid.org/0000-0002-6481-6389"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongxu Yin","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-6481-6389","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086131079","display_name":"Niraj K. Jha","orcid":"https://orcid.org/0000-0002-1539-0369"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niraj K. Jha","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, Princeton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-1539-0369","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":2.8683,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92653581,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":"2","first_page":"752","last_page":"762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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/T12676","display_name":"Machine Learning and ELM","score":0.9955999851226807,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.842048168182373},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7918595671653748},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.7570338845252991},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.670591413974762},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6283354759216309},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5959282517433167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.590201735496521},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.569347620010376},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.523200511932373},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4696585237979889},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11031892895698547},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08617031574249268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.842048168182373},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7918595671653748},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.7570338845252991},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.670591413974762},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6283354759216309},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5959282517433167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590201735496521},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.569347620010376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.523200511932373},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4696585237979889},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11031892895698547},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08617031574249268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2020.3037052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2020.3037052","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5734733387","display_name":null,"funder_award_id":"CNS-1617640","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1467353089","https://openalex.org/W1686810756","https://openalex.org/W1973311433","https://openalex.org/W1996773027","https://openalex.org/W2103753221","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2113911479","https://openalex.org/W2119144962","https://openalex.org/W2160684493","https://openalex.org/W2194775991","https://openalex.org/W2473930607","https://openalex.org/W2510500522","https://openalex.org/W2560017826","https://openalex.org/W2618530766","https://openalex.org/W2620740922","https://openalex.org/W2750384547","https://openalex.org/W2773246426","https://openalex.org/W2774000609","https://openalex.org/W2794664194","https://openalex.org/W2883780447","https://openalex.org/W2912984848","https://openalex.org/W2913686213","https://openalex.org/W2962860144","https://openalex.org/W2963163009","https://openalex.org/W2963319203","https://openalex.org/W2963628712","https://openalex.org/W2963844898","https://openalex.org/W2963918968","https://openalex.org/W2963919236","https://openalex.org/W2974859516","https://openalex.org/W2980137827","https://openalex.org/W2991232789","https://openalex.org/W2995785927","https://openalex.org/W3034957837","https://openalex.org/W3203827521","https://openalex.org/W4319988532","https://openalex.org/W6637373629","https://openalex.org/W6677580257","https://openalex.org/W6679436768","https://openalex.org/W6682132143","https://openalex.org/W6685444988","https://openalex.org/W6687566353","https://openalex.org/W6726268702","https://openalex.org/W6730047919","https://openalex.org/W6743688258","https://openalex.org/W6746839373","https://openalex.org/W6748094767","https://openalex.org/W6748588790","https://openalex.org/W6750362633","https://openalex.org/W6758794888","https://openalex.org/W6767674130","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W2950475743","https://openalex.org/W4386603768","https://openalex.org/W2886711096","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W2590796488","https://openalex.org/W4389249638","https://openalex.org/W2734358244","https://openalex.org/W4388700941","https://openalex.org/W3015200942"],"abstract_inverted_index":{"Deep":[0],"neural":[1,52,61,156],"networks":[2],"(DNNs)":[3],"have":[4],"become":[5],"a":[6,50,106],"widely":[7],"deployed":[8],"model":[9,24,103],"for":[10,113,117,137,160,197,202],"numerous":[11],"machine":[12],"learning":[13,46],"applications.":[14],"However,":[15],"their":[16],"fixed":[17],"architecture,":[18],"substantial":[19],"training":[20,135,146,167,182,208,212],"cost,":[21],"and":[22,97,115,130,149,176,187,217,226],"significant":[23],"redundancy":[25],"make":[26],"it":[27],"difficult":[28],"to":[29,33,71,76,93,141,171,181,243],"efficiently":[30],"update":[31],"them":[32],"accommodate":[34,77],"previously":[35],"unseen":[36],"data.":[37,79],"To":[38],"solve":[39],"these":[40],"problems,":[41],"we":[42],"propose":[43],"an":[44],"incremental":[45],"framework":[47,82,124,165],"based":[48,67,87],"on":[49,68,88],"grow-and-prune":[51,188,218],"network":[53,62,74,95,128,150,157,185,215,236],"synthesis":[54],"paradigm.":[55],"When":[56],"new":[57,65,78],"data":[58,139],"arrive,":[59],"the":[60,69,73,81,89,102,133,153,161,164,193,198,203,206],"first":[63],"grows":[64],"connections":[66,86],"gradients":[70],"increase":[72],"capacity":[75],"Then,":[80],"iteratively":[83],"prunes":[84],"away":[85],"magnitude":[90],"of":[91],"weights":[92],"enhance":[94],"compactness,":[96],"hence":[98],"recover":[99],"efficiency.":[100],"Finally,":[101],"rests":[104],"at":[105],"lightweight":[107],"DNN":[108],"that":[109],"is":[110],"both":[111],"ready":[112],"inference":[114],"suitable":[116],"future":[118],"grow-":[119],"and-prune":[120],"updates.":[121],"The":[122],"proposed":[123],"improves":[125],"accuracy,":[126],"shrinks":[127],"size,":[129],"significantly":[131],"reduces":[132,166],"additional":[134],"cost":[136,168,209],"incoming":[138],"compared":[140,180],"conventional":[142,244],"approaches,":[143],"such":[144],"as":[145],"from":[147,183,189,213,219],"scratch":[148,220],"fine-tuning.":[151],"For":[152,192],"LeNet-300-100":[154],"(LeNet-5)":[155],"architectures":[158],"derived":[159,196,232],"MNIST":[162],"dataset,":[163],"by":[169],"up":[170],"64":[172,222],"(67),":[173,223],"63":[174],"(63),":[175],"69":[177],"(73":[178],"percent)":[179],"scratch,":[184,190,214],"fine-tuning,":[186],"respectively.":[191,230],"ResNet-18":[194],"architecture":[195],"ImageNet":[199],"dataset":[200],"(DeepSpeech2":[201],"AN4":[204],"dataset),":[205],"corresponding":[207],"reductions":[210],"against":[211],"fine-tunning,":[216],"are":[221],"60":[224],"(62),":[225],"72":[227],"(71":[228],"percent),":[229],"Our":[231],"models":[233],"contain":[234],"fewer":[235],"parameters":[237],"but":[238],"achieve":[239],"higher":[240],"accuracy":[241],"relative":[242],"baselines.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}