{"id":"https://openalex.org/W7162629842","doi":"https://doi.org/10.48550/arxiv.2605.28007","title":"Learning Compositional Latent Structure with Vector Networks","display_name":"Learning Compositional Latent Structure with Vector Networks","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162629842","doi":"https://doi.org/10.48550/arxiv.2605.28007"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28007","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28007","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.2605.28007","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137285522","display_name":"Niclas Pokel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pokel, Niclas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133720839","display_name":"Benjamin F. Grewe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grewe, Benjamin F.","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":0.27970001101493835,"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":0.27970001101493835,"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":0.07980000227689743,"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":0.07109999656677246,"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/property","display_name":"Property (philosophy)","score":0.5824000239372253},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5706999897956848},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5164999961853027},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5138999819755554},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4675999879837036},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4519999921321869},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4250999987125397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6074000000953674},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5824000239372253},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4771000146865845},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42640000581741333},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C134466208","wikidata":"https://www.wikidata.org/wiki/Q1520657","display_name":"Weight function","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C25432639","wikidata":"https://www.wikidata.org/wiki/Q3711790","display_name":"Weight distribution","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3296000063419342},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C183877218","wikidata":"https://www.wikidata.org/wiki/Q7979858","display_name":"Weight","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2827000021934509},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28007","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28007","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.2605.28007","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28007","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"networks":[1,171],"are":[2],"powerful":[3],"function":[4],"approximators,":[5],"but":[6],"they":[7],"typically":[8],"store":[9],"many":[10,192],"different":[11],"computations":[12],"in":[13,33,46,148,167],"shared":[14,196],"weight":[15,53,61,78,94,102,115],"matrices,":[16],"making":[17],"it":[18],"difficult":[19],"to":[20,71],"selectively":[21],"reuse":[22],"or":[23],"adapt":[24],"parts":[25],"of":[26,58,76,158,179,190],"them":[27],"when":[28,161],"a":[29,42,51,56,68,73,176,187],"familiar":[30,162],"structure":[31],"appears":[32],"novel":[34,168],"combinations.":[35],"We":[36,126],"introduce":[37],"the":[38,113,123,180],"Vector":[39,170],"Network":[40],"(VN),":[41],"hierarchical":[43],"recurrent":[44],"architecture":[45,181],"which":[47],"each":[48,64],"layer":[49],"replaces":[50],"fixed":[52],"matrix":[54,103],"with":[55],"library":[57],"reusable":[59],"rank-1":[60],"atoms.":[62],"For":[63],"input,":[65],"VN":[66,128,144],"minimizes":[67],"layer-local":[69],"energy":[70],"infer":[72],"sparse":[74],"set":[75],"active":[77],"atoms":[79,116],"and":[80,89,141,182],"their":[81],"coefficients,":[82],"jointly":[83],"constrained":[84],"by":[85,122],"bottom-up":[86],"input":[87],"reconstruction":[88],"top-down":[90],"feedback":[91],"consistency.":[92],"These":[93],"atom":[95],"coefficients":[96],"then":[97],"compose":[98],"an":[99,156],"input-specific":[100],"low-rank":[101],"for":[104],"that":[105],"sample.":[106],"After":[107],"convergence,":[108],"slow":[109],"learning":[110],"updates":[111],"only":[112],"selected":[114],"through":[117],"local":[118],"residual":[119],"signals":[120],"scaled":[121],"inferred":[124],"coefficients.":[125],"evaluate":[127],"on":[129],"four":[130],"compositional":[131,142,174],"benchmarks":[132],"spanning":[133],"1D":[134],"signals,":[135],"2D":[136],"spatial":[137],"decoding,":[138],"N-body":[139],"dynamics,":[140],"MNIST.":[143],"matches":[145],"strong":[146],"baselines":[147],"distribution":[149],"while":[150],"often":[151],"achieving":[152],"out-of-distribution":[153],"error":[154],"about":[155],"order":[157],"magnitude":[159],"lower":[160],"factors":[163],"must":[164],"be":[165],"recombined":[166],"ways.":[169],"thus":[172],"make":[173],"generalization":[175],"structural":[177],"property":[178],"inference":[183],"process":[184],"rather":[185],"than":[186],"brittle":[188],"byproduct":[189],"fitting":[191],"behaviors":[193],"into":[194],"one":[195],"dense":[197],"parameter":[198],"substrate.":[199]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-29T00:00:00"}