{"id":"https://openalex.org/W7161594837","doi":"https://doi.org/10.48550/arxiv.2605.15306","title":"How Data Augmentation Shapes Neural Representations","display_name":"How Data Augmentation Shapes Neural Representations","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161594837","doi":"https://doi.org/10.48550/arxiv.2605.15306"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15306","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15306","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.15306","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101878219","display_name":"Tianxi He","orcid":"https://orcid.org/0000-0002-8996-9082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Tianxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136443250","display_name":"Alex H. Williams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Williams, Alex H.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005430139","display_name":"Sarah E. Harvey","orcid":"https://orcid.org/0000-0003-2601-7487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harvey, Sarah E.","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.193900004029274,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.193900004029274,"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/T12417","display_name":"Morphological variations and asymmetry","score":0.14800000190734863,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.10989999771118164,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6651999950408936},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6064000129699707},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.589900016784668},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5773000121116638},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5516999959945679},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46000000834465027},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.397599995136261}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6651999950408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6617000102996826},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6064000129699707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5996000170707703},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.589900016784668},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.39340001344680786},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C112604564","wikidata":"https://www.wikidata.org/wiki/Q7489226","display_name":"Shape analysis (program analysis)","level":3,"score":0.3248000144958496},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C32990609","wikidata":"https://www.wikidata.org/wiki/Q306542","display_name":"Transformation geometry","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15306","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15306","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.15306","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15306","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"Data":[0],"augmentation":[1,31,67,79,97,142],"is":[2,55],"widely":[3],"recognized":[4],"for":[5,137],"improving":[6],"generalization":[7],"in":[8,36,73,83],"deep":[9],"networks,":[10],"yet":[11],"its":[12],"impact":[13],"on":[14],"the":[15,111],"geometry":[16,105],"of":[17],"learned":[18],"representations":[19,35,48,82,109],"remains":[20],"poorly":[21],"understood.":[22],"In":[23],"this":[24,74],"work,":[25],"we":[26,44,87],"characterize":[27],"how":[28,89],"different":[29,78],"data":[30,96,141],"strategies":[32],"reshape":[33],"internal":[34],"neural":[37,90,104],"networks.":[38],"Using":[39],"tools":[40],"from":[41,103],"shape":[42],"analysis,":[43],"embed":[45],"network":[46],"hidden":[47],"into":[49],"a":[50,134],"metric":[51],"space":[52],"where":[53],"distance":[54],"invariant":[56],"to":[57,70],"scaling,":[58],"translation,":[59],"rotation":[60],"and":[61,76,99,125,127,139],"reflection.":[62],"We":[63],"show":[64,100],"that":[65,77,101,129],"increasing":[66],"strength":[68],"leads":[69],"well-behaved":[71],"trajectories":[72,132],"space,":[75],"types":[80],"steer":[81],"distinct":[84],"directions.":[85],"Moreover,":[86],"investigate":[88],"representation":[91],"shapes":[92],"are":[93],"distorted":[94],"along":[95],"trajectories,":[98],"insights":[102],"can":[106],"predict":[107],"which":[108],"provide":[110],"most":[112],"improvement":[113],"when":[114],"ensembling":[115],"models.":[116],"Our":[117],"results":[118],"reveal":[119],"shared":[120],"geometric":[121],"patterns":[122],"across":[123],"architectures":[124],"seeds,":[126],"suggest":[128],"analyzing":[130],"shape-space":[131],"offers":[133],"principled":[135],"tool":[136],"understanding":[138],"comparing":[140],"methods.":[143]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-19T00:00:00"}