{"id":"https://openalex.org/W7169776944","doi":"https://doi.org/10.48550/arxiv.2607.15745","title":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","display_name":"Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training","publication_year":2026,"publication_date":"2026-07-17","ids":{"openalex":"https://openalex.org/W7169776944","doi":"https://doi.org/10.48550/arxiv.2607.15745"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.15745","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15745","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.15745","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049003585","display_name":"A. Shehu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shehu, Anxhelo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141216384","display_name":"Enes Stastoli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stastoli, Enes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047719086","display_name":"Arben \u00c7ela","orcid":"https://orcid.org/0000-0001-5708-1743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cela, Arben","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8689000010490417,"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":0.8689000010490417,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03229999914765358,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.016599999740719795,"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/hyperparameter","display_name":"Hyperparameter","score":0.6128000020980835},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5202999711036682},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.507099986076355},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.5008000135421753},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4307999908924103},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4187999963760376},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.4016999900341034},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38089999556541443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870000004768372},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6128000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5311999917030334},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5077999830245972},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C126661757","wikidata":"https://www.wikidata.org/wiki/Q4925641","display_name":"Random search","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.15745","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15745","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.15745","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15745","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Common":[0],"practice":[1],"when":[2],"training":[3],"Convolutional":[4],"Neural":[5],"Networks":[6],"(CNNs)":[7],"is":[8,59],"to":[9,164,221],"use":[10],"randomly":[11],"shuffled":[12],"mini-batches.":[13],"This":[14,83],"creates":[15],"two":[16],"limitations:":[17],"slower":[18],"convergence,":[19],"and":[20,68,88,133,153,171,197],"a":[21,44,53,62,65,75,80,121,217],"diminishing":[22],"learning":[23],"signal,":[24],"since":[25],"many":[26],"samples":[27],"are":[28],"quickly":[29],"classified":[30],"as":[31,52,61],"easy":[32],"during":[33],"training.":[34],"We":[35,107],"address":[36],"these":[37,143],"inefficiencies":[38],"with":[39,79,148,159,190,224],"A*-Inspired":[40],"Batch":[41],"Selection":[42],"(A*-BS),":[43],"lightweight,":[45],"model-agnostic":[46],"strategy":[47],"that":[48,205],"formulates":[49],"mini-batch":[50],"scheduling":[51],"heuristic":[54],"search":[55,66],"problem.":[56],"Each":[57],"batch":[58,89,177,207],"treated":[60],"node":[63],"in":[64],"space":[67],"ranked":[69],"using":[70,120],"an":[71],"A*-like":[72],"score":[73],"combining":[74],"loss-based":[76],"difficulty":[77],"measure":[78],"reuse":[81],"penalty.":[82],"encourages":[84],"informative":[85],"gradient":[86],"updates":[87],"diversity":[90],"throughout":[91],"training,":[92],"without":[93],"modifying":[94],"network":[95],"architectures":[96],"or":[97],"optimization":[98],"algorithms,":[99],"so":[100],"it":[101],"integrates":[102],"seamlessly":[103],"into":[104],"existing":[105],"pipelines.":[106],"evaluate":[108],"A*-BS":[109,149,174,191],"on":[110,179,199],"the":[111,117,131,138,145,187],"twelve":[112,181],"2D":[113],"classification":[114],"tasks":[115],"of":[116,125,142,162],"MedMNIST-v2":[118],"benchmark,":[119],"deliberately":[122],"simple":[123],"architecture":[124,170],"approximately":[126],"2.25x10^5":[127],"parameters,":[128],"compared":[129],"against":[130,231],"ResNet-18":[132,196],"ResNet-50":[134,198],"baselines":[135],"reported":[136],"by":[137,227],"benchmark.":[139],"On":[140],"half":[141],"tasks,":[144],"lightweight":[146,188],"model":[147],"reaches":[150],"higher":[151],"accuracy":[152],"AUC":[154],"than":[155,195],"both":[156],"ResNet":[157],"baselines,":[158],"relative":[160],"gains":[161],"up":[163],"15%.":[165],"An":[166],"ablation":[167],"under":[168],"identical":[169,200],"hyperparameters":[172],"shows":[173],"outperforms":[175],"random":[176],"shuffling":[178],"all":[180],"tasks.":[182],"Wall-clock":[183],"measurements":[184],"further":[185],"show":[186],"CNN":[189],"trains":[192],"substantially":[193],"faster":[194],"hardware.":[201],"These":[202],"results":[203],"indicate":[204],"intelligent":[206],"ordering":[208],"can":[209],"partially":[210],"compensate":[211],"for":[212],"reduced":[213],"architectural":[214],"complexity,":[215],"offering":[216],"computationally":[218],"efficient":[219],"alternative":[220],"deeper":[222],"models,":[223],"reliability":[225],"reinforced":[226],"strong":[228],"performance":[229],"even":[230],"deeper,":[232],"more":[233],"sophisticated":[234],"architectures.":[235]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-21T00:00:00"}