{"id":"https://openalex.org/W7167677943","doi":"https://doi.org/10.48550/arxiv.2607.05908","title":"Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift","display_name":"Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift","publication_year":2026,"publication_date":"2026-07-07","ids":{"openalex":"https://openalex.org/W7167677943","doi":"https://doi.org/10.48550/arxiv.2607.05908"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.05908","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.05908","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":"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.2607.05908","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139239428","display_name":"Robin Holzinger","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Holzinger, Robin","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140278750","display_name":"Riccardo Colletti","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colletti, Riccardo","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"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/T12761","display_name":"Data Stream Mining Techniques","score":0.6308000087738037,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.6308000087738037,"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":0.05000000074505806,"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":0.039400000125169754,"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/robustness","display_name":"Robustness (evolution)","score":0.7918000221252441},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5889000296592712},{"id":"https://openalex.org/keywords/concept-drift","display_name":"Concept drift","score":0.5198000073432922},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5152999758720398},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"Inductive bias","score":0.4975000023841858},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42820000648498535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41110000014305115},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38940000534057617},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.38670000433921814}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7918000221252441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347000241279602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6029000282287598},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5327000021934509},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.5198000073432922},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5152999758720398},{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.4975000023841858},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.25189998745918274},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.05908","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.05908","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":"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.2607.05908","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.05908","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":"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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7056713700294495}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"data":[1,79],"distributions":[2],"evolve":[3],"over":[4,154],"time,":[5,155],"inducing":[6],"temporal":[7,34,46,70,125,187],"distribution":[8],"shift":[9],"that":[10,119,151,164],"can":[11],"substantially":[12],"degrade":[13,159],"the":[14,22,116,140,149],"reliability":[15],"of":[16,45],"deployed":[17],"machine":[18],"learning":[19],"systems.":[20],"However,":[21],"extent":[23],"to":[24,108,133,186],"which":[25],"architectural":[26,120],"choices":[27],"and":[28,59,80,87,105,111],"their":[29,82],"associated":[30],"inductive":[31,121,129],"biases":[32,122,130],"affect":[33],"robustness":[35,47],"remains":[36],"insufficiently":[37],"understood.":[38],"We":[39],"present":[40],"a":[41,64],"systematic":[42],"empirical":[43],"comparison":[44],"across":[48],"three":[49],"heterogeneous,":[50],"time-indexed":[51],"domains":[52],"encompassing":[53],"image":[54],"classification,":[55,58],"multi-label":[56],"text":[57,60],"regression":[61],"tasks.":[62],"Using":[63],"unified":[65],"evaluation":[66],"framework":[67],"based":[68],"on":[69,76,84,166],"drift":[71,171],"matrices,":[72],"we":[73],"train":[74],"models":[75,127,158],"cumulative":[77],"historical":[78],"evaluate":[81],"performance":[83],"both":[85],"earlier":[86],"later":[88],"time":[89],"periods,":[90],"thereby":[91],"quantifying":[92],"cross-temporal":[93],"generalization.":[94],"Our":[95],"study":[96],"spans":[97],"model":[98],"families":[99],"ranging":[100],"from":[101],"simple":[102],"multilayer":[103],"perceptrons":[104],"convolutional":[106],"networks":[107,110],"recurrent":[109],"pretrained":[112,162],"Transformer-based":[113],"encoders.":[114],"Collectively,":[115],"results":[117],"show":[118],"systematically":[123],"shape":[124],"robustness:":[126],"whose":[128],"lead":[131],"them":[132],"exploit":[134],"localized,":[135],"highly":[136],"discriminative":[137],"features":[138,146],"attain":[139],"highest":[141],"in-distribution":[142],"accuracy,":[143],"yet":[144],"those":[145],"are":[147],"often":[148],"ones":[150],"change":[152],"most":[153],"so":[156],"these":[157],"fastest,":[160],"while":[161],"encoders":[163],"draw":[165],"coarser,":[167],"more":[168,172],"stable":[169],"representations":[170],"gradually.":[173],"These":[174],"observations":[175],"offer":[176],"practical":[177],"guidance":[178],"for":[179,182],"selecting":[180],"architectures":[181],"real-world":[183],"systems":[184],"subject":[185],"drift.":[188]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-09T00:00:00"}