{"id":"https://openalex.org/W7139012893","doi":"https://doi.org/10.48550/arxiv.2603.16513","title":"FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data","display_name":"FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7139012893","doi":"https://doi.org/10.48550/arxiv.2603.16513"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16513","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16513","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.16513","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129873028","display_name":"Zhenghang Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Song, Zhenghang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129859284","display_name":"Tang Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Tang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130018803","display_name":"Lu Chen (15109817)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111215311","display_name":"Yushuai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yushuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129863513","display_name":"Zhengke Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zhengke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129813222","display_name":"Bingbing Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Bingbing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130165339","display_name":"Yumeng Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Yumeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129846925","display_name":"Junbo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Junbo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129865816","display_name":"Sheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Sheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129986897","display_name":"Tianyi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Tianyi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5129873028"],"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/T13702","display_name":"Machine Learning in Healthcare","score":0.6646000146865845,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.6646000146865845,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05920000001788139,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02969999983906746,"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/pipeline","display_name":"Pipeline (software)","score":0.5782999992370605},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4887000024318695},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.46399998664855957},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.45419999957084656},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4002000093460083},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.367000013589859},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.36570000648498535},{"id":"https://openalex.org/keywords/linear-model","display_name":"Linear model","score":0.3531000018119812},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.3450999855995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476999759674072},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5081999897956848},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49000000953674316},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.3249000012874603},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C153185123","wikidata":"https://www.wikidata.org/wiki/Q1391624","display_name":"Sequence diagram","level":4,"score":0.2759999930858612},{"id":"https://openalex.org/C170122806","wikidata":"https://www.wikidata.org/wiki/Q1914828","display_name":"Linear scale","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16513","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16513","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.16513","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16513","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Structured":[0],"data":[1,10],"is":[2],"foundational":[3],"to":[4,21,61,73,168],"healthcare,":[5],"finance,":[6],"e-commerce,":[7],"and":[8,31,64,113,143,165],"scientific":[9],"management.":[11],"Large":[12],"structured-data":[13],"models":[14,56],"(LDMs)":[15],"extend":[16],"the":[17,50],"foundation":[18,82],"model":[19,83,141],"paradigm":[20],"unify":[22],"heterogeneous":[23],"datasets":[24,152],"for":[25,84,109,119],"tasks":[26],"such":[27],"as":[28],"classification,":[29],"regression,":[30],"decision":[32],"support.":[33],"However,":[34],"existing":[35],"LDMs":[36],"face":[37],"major":[38],"limitations.":[39],"First,":[40],"most":[41],"rely":[42],"on":[43,149],"sample-wise":[44],"self-attention,":[45],"whose":[46],"O(N^2)":[47],"complexity":[48],"limits":[49],"sample":[51,111],"count.":[52],"Second,":[53],"linear":[54,101,116],"sequence":[55],"often":[57,71],"degrade":[58],"representations":[59],"due":[60],"hidden-state":[62],"compression":[63],"artificial":[65],"causal":[66,140],"bias.":[67],"Third,":[68],"synthetic-only":[69],"pre-training":[70],"fails":[72],"match":[74],"real-world":[75,151],"distributions.":[76],"We":[77],"propose":[78],"FEAT,":[79],"a":[80,91,137,144],"linear-complexity":[81,125],"extremely":[85],"large":[86],"structured":[87],"data.":[88],"FEAT":[89,135,155],"introduces":[90],"multi-layer":[92],"dual-axis":[93],"architecture":[94,104],"that":[95,154],"replaces":[96],"quadratic":[97],"attention":[98,117],"with":[99],"hybrid":[100,138],"encoding.":[102],"The":[103],"combines":[105],"adaptive-fusion":[106],"bi-Mamba-2":[107],"(AFBM)":[108],"local":[110],"dependencies":[112],"convolutional":[114],"gated":[115],"(Conv-GLA)":[118],"global":[120],"memory.":[121],"This":[122],"design":[123],"enables":[124],"cross-sample":[126],"modeling":[127],"while":[128,162],"preserving":[129],"expressive":[130],"representations.":[131],"To":[132],"improve":[133],"robustness,":[134],"adopts":[136],"structural":[139],"pipeline":[142],"stable":[145],"reconstruction":[146],"objective.":[147],"Experiments":[148],"11":[150],"show":[153],"consistently":[156],"outperforms":[157],"baselines":[158],"in":[159],"zero-shot":[160],"performance,":[161],"scaling":[163],"linearly":[164],"achieving":[166],"up":[167],"40x":[169],"faster":[170],"inference.":[171]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}