{"id":"https://openalex.org/W7157110828","doi":"https://doi.org/10.48550/arxiv.2604.24313","title":"Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks","display_name":"Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7157110828","doi":"https://doi.org/10.48550/arxiv.2604.24313"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24313","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24313","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.2604.24313","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124724911","display_name":"WonYong CHO","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cho, Wonyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134784095","display_name":"Taemin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Taemin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134811690","display_name":"Jungmin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Jungmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134790951","display_name":"Jeong-Rae Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Jeong-Rae","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103357797","display_name":"Sung Hoon Jung","orcid":"https://orcid.org/0000-0002-9674-4543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jung, Sung Hoon","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3285999894142151,"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":0.3285999894142151,"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":0.19900000095367432,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.09709999710321426,"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/overfitting","display_name":"Overfitting","score":0.8475000262260437},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6765999794006348},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6549999713897705},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6075000166893005},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6017000079154968},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5252000093460083},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.46070000529289246}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8475000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7843000292778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432000041007996},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6765999794006348},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6549999713897705},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5252000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5232999920845032},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C2988224531","wikidata":"https://www.wikidata.org/wiki/Q20830730","display_name":"Network structure","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2987015589","wikidata":"https://www.wikidata.org/wiki/Q1040098","display_name":"Learning network","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24313","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24313","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.2604.24313","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24313","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"large-scale":[1],"deep":[2,12,95],"neural":[3],"networks":[4,53,81],"effectively":[5,87],"and":[6,36,67,70,102,118],"stably":[7],"is":[8,64],"essential":[9],"for":[10,76],"applying":[11],"learning":[13],"across":[14,99],"various":[15],"fields.":[16],"However,":[17],"conventional":[18,110],"methods,":[19,111],"which":[20],"rely":[21],"on":[22],"training":[23,93],"a":[24,48],"single":[25],"large":[26],"network,":[27],"often":[28],"encounter":[29],"challenges":[30],"such":[31],"as":[32,74],"gradient":[33],"vanishing,":[34],"overfitting":[35],"unstable":[37],"learning.":[38],"To":[39],"overcome":[40],"these":[41],"limitations,":[42],"we":[43],"introduce":[44],"Self-Abstraction":[45],"Learning":[46],"(SAL),":[47],"hierarchical":[49],"framework.":[50],"In":[51],"SAL,":[52],"are":[54],"arranged":[55],"by":[56],"structural":[57],"complexity,":[58],"where":[59],"the":[60,77],"simplest":[61],"topmost":[62],"network":[63,120],"trained":[65],"first":[66],"its":[68],"hidden":[69],"output":[71],"layers":[72],"serve":[73],"guidance":[75,86],"successively":[78],"more":[79],"complex":[80,119],"below.":[82],"This":[83],"top-down":[84],"sequential":[85],"mitigates":[88],"optimization":[89],"issues,":[90],"enabling":[91],"stable":[92],"of":[94],"architectures.":[96],"Various":[97],"experiments":[98],"MLP,":[100],"CNN,":[101],"RNN":[103],"architectures":[104],"demonstrate":[105],"that":[106],"SAL":[107],"consistently":[108],"outperforms":[109],"ensuring":[112],"robust":[113],"generalization":[114],"even":[115],"in":[116],"data-scarce":[117],"regimes.":[121]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-29T00:00:00"}