{"id":"https://openalex.org/W7126242962","doi":"https://doi.org/10.1109/access.2026.3659474","title":"Memory-Efficient and Trustworthy Neural Networks via Random Seed-Based Design","display_name":"Memory-Efficient and Trustworthy Neural Networks via Random Seed-Based Design","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7126242962","doi":"https://doi.org/10.1109/access.2026.3659474"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3659474","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3659474","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3659474","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014964663","display_name":"Hiroaki Ito","orcid":"https://orcid.org/0000-0003-3769-7115"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroaki Ito","raw_affiliation_strings":["1Institute of Science Tokyo, Yokohama, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"1Institute of Science Tokyo, Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113066142","display_name":"Hikari Otsuka","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hikari Otsuka","raw_affiliation_strings":["1Institute of Science Tokyo, Yokohama, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"1Institute of Science Tokyo, Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124343472","display_name":"Ryota Yasudo","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Yasudo","raw_affiliation_strings":["2Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"2Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122838684","display_name":"Zhiqiang Walkie Que","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144746","display_name":"The London College","ror":"https://ror.org/0546ajs61","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210144746"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhiqiang Que","raw_affiliation_strings":["3Imperial College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"3Imperial College London, London, U.K","institution_ids":["https://openalex.org/I4210144746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123417783","display_name":"Jose G. F. Coutinho","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144746","display_name":"The London College","ror":"https://ror.org/0546ajs61","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210144746"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jose G. F. Coutinho","raw_affiliation_strings":["3Imperial College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"3Imperial College London, London, U.K","institution_ids":["https://openalex.org/I4210144746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058871698","display_name":"Daichi Fujiki","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Fujiki","raw_affiliation_strings":["1Institute of Science Tokyo, Yokohama, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"1Institute of Science Tokyo, Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089388923","display_name":"Masato Motomura","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Motomura","raw_affiliation_strings":["1Institute of Science Tokyo, Yokohama, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"1Institute of Science Tokyo, Yokohama, Kanagawa, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083303676","display_name":"Ce Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144746","display_name":"The London College","ror":"https://ror.org/0546ajs61","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210144746"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ce Guo","raw_affiliation_strings":["3Imperial College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"3Imperial College London, London, U.K","institution_ids":["https://openalex.org/I4210144746"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110068140","display_name":"W. Luk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144746","display_name":"The London College","ror":"https://ror.org/0546ajs61","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210144746"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wayne Luk","raw_affiliation_strings":["3Imperial College London, London, U.K"],"affiliations":[{"raw_affiliation_string":"3Imperial College London, London, U.K","institution_ids":["https://openalex.org/I4210144746"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5014964663"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2456777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"19424","last_page":"19439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9146000146865845,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9146000146865845,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.023800000548362732,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.009700000286102295,"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/randomness","display_name":"Randomness","score":0.5559999942779541},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47530001401901245},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.3774000108242035},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3517000079154968},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.3325999975204468},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3319999873638153},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.33160001039505005},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.3294999897480011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3287000060081482},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.31040000915527344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149999976158142},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4846000075340271},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47350001335144043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41589999198913574},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3752000033855438},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C168773036","wikidata":"https://www.wikidata.org/wiki/Q264164","display_name":"Recursion (computer science)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2780971903","wikidata":"https://www.wikidata.org/wiki/Q2933705","display_name":"Stochastic computing","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2026.3659474","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3659474","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:daadddcc69f643fc904a391e27e23999","is_oa":true,"landing_page_url":"https://doaj.org/article/daadddcc69f643fc904a391e27e23999","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 19424-19439 (2026)","raw_type":"article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50752077","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100941379","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3659474","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3659474","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2153959628","https://openalex.org/W2194775991","https://openalex.org/W3034234149","https://openalex.org/W3217694566","https://openalex.org/W4213433078","https://openalex.org/W4226337850","https://openalex.org/W4410400416"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"models":[2,36,184],"deployed":[3,101],"in":[4],"resource-constrained":[5],"and":[6,14,19,32,44,48,76,93,111,138,141,158,167,178,208,223],"safety-critical":[7],"settings":[8],"must":[9],"be":[10,104],"not":[11],"only":[12],"compact":[13],"accurate":[15],"but":[16],"also":[17],"trustworthy":[18],"capable":[20],"of":[21,115,119,190,206],"expressing":[22],"predictive":[23,179],"uncertainty.":[24],"However,":[25],"conventional":[26],"compression":[27,222],"techniques":[28],"such":[29],"as":[30,128,229],"pruning":[31],"quantization":[33],"often":[34],"make":[35],"overconfident,":[37],"while":[38],"uncertainty-aware":[39],"methods":[40],"like":[41],"Bayesian":[42,145],"inference":[43],"ensembles":[45],"ignore":[46],"memory":[47,139],"compute":[49],"budgets.":[50],"In":[51],"this":[52,125],"work,":[53],"we":[54],"propose":[55],"Random":[56,79],"Seed-Based":[57],"Design,":[58],"a":[59,67,100,112,129],"framework":[60],"that":[61,99,185,216],"elevates":[62],"the":[63],"random":[64],"seed":[65],"to":[66,152,188,203],"first-class":[68],"design":[69,131,149],"primitive":[70],"for":[71],"jointly":[72],"shaping":[73],"sparsity,":[74],"freezing,":[75],"stochastic":[77,84],"inference.":[78],"seeds":[80],"deterministically":[81],"generate":[82],"all":[83],"components:":[85],"Strong":[86],"Lottery":[87],"Ticket":[88],"weights,":[89],"partially":[90],"frozen":[91],"masks,":[92,97,110],"Monte":[94],"Carlo":[95],"Dropout":[96],"so":[98],"model":[102],"can":[103],"exactly":[105],"regenerated":[106],"from":[107],"seeds,":[108],"binary":[109],"small":[113],"set":[114],"interpretable":[116],"hyperparameters":[117],"instead":[118],"dense":[120,195],"weight":[121],"tensors.":[122],"We":[123],"formulate":[124],"seed-based":[126,148],"construction":[127],"multi-objective":[130],"problem":[132],"over":[133],"accuracy,":[134],"calibration,":[135],"uncertainty,":[136],"FLOP,":[137],"footprint,":[140],"solve":[142],"it":[143],"with":[144],"optimization.":[146],"This":[147],"enables":[150],"us":[151],"characterize":[153],"Pareto-optimal":[154],"trade-offs":[155],"between":[156,175],"efficiency":[157,177],"trustworthiness":[159],"across":[160],"diverse":[161],"architectures,":[162],"including":[163],"convolutional":[164],"neural":[165,169],"networks":[166],"graph":[168],"networks,":[170],"thereby":[171],"illuminating":[172],"domain-dependent":[173],"relationships":[174],"computational":[176],"reliability.":[180],"Our":[181],"method":[182],"discovers":[183],"are":[186],"tens":[187],"hundreds":[189],"times":[191],"smaller":[192],"than":[193,226],"their":[194],"counterparts,":[196],"reduces":[197],"expected":[198],"calibration":[199],"error":[200],"by":[201],"up":[202],"an":[204],"order":[205],"magnitude,":[207],"matches":[209],"or":[210],"improves":[211,220],"accuracy.":[212],"These":[213],"results":[214],"show":[215],"structured":[217],"seed-controlled":[218],"randomness":[219],"both":[221],"trustworthiness,":[224],"rather":[225],"treating":[227],"them":[228],"competing":[230],"objectives.":[231],"The":[232],"source":[233],"code":[234],"is":[235],"available":[236],"at":[237],"https://github.com/itocha/SLT-TRUST.":[238]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-01T00:00:00"}