{"id":"https://openalex.org/W4402250122","doi":"https://doi.org/10.3389/frai.2024.1387936","title":"MixTrain: accelerating DNN training via input mixing","display_name":"MixTrain: accelerating DNN training via input mixing","publication_year":2024,"publication_date":"2024-09-04","ids":{"openalex":"https://openalex.org/W4402250122","doi":"https://doi.org/10.3389/frai.2024.1387936","pmid":"https://pubmed.ncbi.nlm.nih.gov/39355147"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2024.1387936","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1387936","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1387936/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1387936/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075611664","display_name":"Sarada Krithivasan","orcid":"https://orcid.org/0000-0002-2958-1377"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sarada Krithivasan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, United States","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021284824","display_name":"Sanchari Sen","orcid":"https://orcid.org/0000-0003-0080-2882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanchari Sen","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010094713","display_name":"Swagath Venkataramani","orcid":"https://orcid.org/0000-0002-0470-6364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swagath Venkataramani","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065766721","display_name":"Anand Raghunathan","orcid":"https://orcid.org/0000-0002-4624-564X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Raghunathan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, United States","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075611664"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10668925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"1387936","last_page":"1387936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/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/T12535","display_name":"Machine Learning and Data Classification","score":0.9980000257492065,"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":0.784869909286499},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6279093027114868},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.5587906837463379},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5483601093292236},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49045702815055847},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4332994222640991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36596617102622986},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35270416736602783}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784869909286499},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6279093027114868},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5587906837463379},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5483601093292236},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49045702815055847},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4332994222640991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36596617102622986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35270416736602783},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frai.2024.1387936","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1387936","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1387936/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:39355147","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39355147","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11443600","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11443600","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11443600/pdf/frai-07-1387936.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Artif Intell","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:d6f9b553a14041159bedc14dd9e23170","is_oa":true,"landing_page_url":"https://doaj.org/article/d6f9b553a14041159bedc14dd9e23170","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2024.1387936","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1387936","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1387936/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.800000011920929,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402250122.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1522301498","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2622263826","https://openalex.org/W2749988060","https://openalex.org/W2765407302","https://openalex.org/W2769856846","https://openalex.org/W2783000019","https://openalex.org/W2963809228","https://openalex.org/W2992308087","https://openalex.org/W3037138603","https://openalex.org/W3094502228","https://openalex.org/W3099584108","https://openalex.org/W3126019867","https://openalex.org/W3145444543","https://openalex.org/W3171975124","https://openalex.org/W3175527903","https://openalex.org/W4206648492","https://openalex.org/W4287077733","https://openalex.org/W4288100995","https://openalex.org/W4288335875","https://openalex.org/W4390675624","https://openalex.org/W6604254268","https://openalex.org/W6631190155","https://openalex.org/W6687483927","https://openalex.org/W6739622702","https://openalex.org/W6743289643","https://openalex.org/W6745136726","https://openalex.org/W6746514494","https://openalex.org/W6759100796","https://openalex.org/W6762058618","https://openalex.org/W6762226699","https://openalex.org/W6763310536","https://openalex.org/W6767032739","https://openalex.org/W6768926992","https://openalex.org/W6771550294","https://openalex.org/W6779606177","https://openalex.org/W6780241430","https://openalex.org/W6781359717","https://openalex.org/W6784333009","https://openalex.org/W6785700070","https://openalex.org/W6787612385","https://openalex.org/W6788146793","https://openalex.org/W6790503700","https://openalex.org/W6793164127","https://openalex.org/W6796435857","https://openalex.org/W6798413682","https://openalex.org/W6800994414"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2784269775","https://openalex.org/W2952904874"],"abstract_inverted_index":{"Training":[0],"Deep":[1],"Neural":[2],"Networks":[3],"(DNNs)":[4],"places":[5],"immense":[6],"compute":[7],"requirements":[8],"on":[9,76,88,162,200,256],"the":[10,26,31,49,77,90,137,141,167,174,178,181,185,193,213,216,250],"underlying":[11],"hardware":[12],"platforms,":[13],"expending":[14],"large":[15],"amounts":[16],"of":[17,51,102,140,169,180,196,215,229],"time":[18],"and":[19,130,152,233,243,252],"energy.":[20],"An":[21],"important":[22],"factor":[23],"contributing":[24],"to":[25,36,80,106,123,134,148,210,222],"long":[27],"training":[28,75,86,114,154,217,248],"times":[29],"is":[30,73,220],"increasing":[32],"dataset":[33,218],"complexity":[34],"required":[35],"reach":[37],"state-of-the-art":[38],"performance":[39,129],"in":[40,98,109,127,184,203,224,247,265],"real-world":[41],"applications.":[42],"To":[43],"address":[44,149],"this":[45,150],"challenge,":[46],"we":[47,165,207,238],"explore":[48],"use":[50],"input":[52,63,79,120,157],"mixing,":[53],"where":[54],"multiple":[55],"inputs":[56,92,103,183,198],"are":[57],"combined":[58],"into":[59],"a":[60,82,99,124],"single":[61],"composite":[62,67],"with":[64,159,262],"an":[65,257],"associated":[66],"label":[68],"for":[69,74,249],"training.":[70],"The":[71],"goal":[72],"mixed":[78,142],"achieve":[81],"similar":[83],"effect":[84],"as":[85],"separately":[87],"each":[89,110,225],"constituent":[91,182,197],"that":[93,118,219],"it":[94],"represents.":[95],"This":[96],"results":[97],"lower":[100],"number":[101],"(or":[104],"mini-batches)":[105],"be":[107],"processed":[108],"epoch,":[111],"proportionally":[112],"reducing":[113],"time.":[115],"We":[116,144,189],"find":[117],"naive":[119],"mixing":[121,158,194,223],"leads":[122],"considerable":[125],"drop":[126],"learning":[128],"model":[131],"accuracy":[132],"due":[133],"interference":[135,171],"between":[136,177],"forward/backward":[138],"propagation":[139],"inputs.":[143],"propose":[145,208],"two":[146,234],"strategies":[147],"challenge":[151],"realize":[153],"speedups":[155,246],"from":[156],"minimal":[160],"impact":[161,168],"accuracy.":[163,267],"First,":[164],"reduce":[166],"inter-input":[170],"by":[172],"exploiting":[173],"spatial":[175],"separation":[176],"features":[179],"network's":[186],"intermediate":[187],"representations.":[188],"also":[190],"adaptively":[191],"vary":[192],"ratio":[195],"based":[199],"their":[201],"loss":[202,264],"previous":[204],"epochs.":[205],"Second,":[206],"heuristics":[209],"automatically":[211],"identify":[212],"subset":[214],"subject":[221],"epoch.":[226],"Across":[227],"ResNets":[228],"varying":[230],"depth,":[231],"MobileNetV2":[232],"Vision":[235],"Transformer":[236],"networks,":[237],"obtain":[239],"upto":[240],"1.6":[241],"\u00d7":[242,245],"1.8":[244],"ImageNet":[251],"Cifar10":[253],"datasets,":[254],"respectively,":[255],"Nvidia":[258],"RTX":[259],"2080Ti":[260],"GPU,":[261],"negligible":[263],"classification":[266]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}