{"id":"https://openalex.org/W7151305013","doi":"https://doi.org/10.48550/arxiv.2604.03582","title":"Simple yet Effective: Low-Rank Spatial Attention for Neural Operators","display_name":"Simple yet Effective: Low-Rank Spatial Attention for Neural Operators","publication_year":2026,"publication_date":"2026-04-04","ids":{"openalex":"https://openalex.org/W7151305013","doi":"https://doi.org/10.48550/arxiv.2604.03582"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.03582","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03582","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.2604.03582","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133131196","display_name":"Zherui Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zherui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037608778","display_name":"Haiyang Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin, Haiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133123220","display_name":"Tao Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044705151","display_name":"Ligang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ligang","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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.0017999999690800905,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.6917999982833862},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6097000241279602},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5135999917984009},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.45500001311302185},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3695000112056732},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.35519999265670776}],"concepts":[{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.6917999982833862},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5501999855041504},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.45500001311302185},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3571999967098236},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3443000018596649},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C27156116","wikidata":"https://www.wikidata.org/wiki/Q1778098","display_name":"Pointwise convergence","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.03582","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03582","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.2604.03582","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03582","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":{"Neural":[0],"operators":[1,64],"have":[2],"emerged":[3],"as":[4,103],"data-driven":[5],"surrogates":[6],"for":[7],"solving":[8],"partial":[9],"differential":[10],"equations":[11],"(PDEs),":[12],"and":[13,84,106,136,148,182],"their":[14],"success":[15],"hinges":[16],"on":[17,119],"efficiently":[18],"modeling":[19],"the":[20,29,36,86],"long-range,":[21],"global":[22,38,59,80,87],"coupling":[23],"among":[24],"spatial":[25,91],"points":[26],"induced":[27,37],"by":[28,94],"underlying":[30],"physics.":[31],"In":[32,154],"many":[33],"PDE":[34],"regimes,":[35],"interaction":[39],"kernels":[40],"are":[41],"empirically":[42],"compressible,":[43],"exhibiting":[44],"rapid":[45],"spectral":[46],"decay":[47],"that":[48,116,143],"admits":[49],"low-rank":[50,68],"approximations.":[51],"We":[52],"leverage":[53],"this":[54,95,110],"observation":[55],"to":[56,90,146,163,176],"unify":[57],"representative":[58],"mixing":[60],"modules":[61],"in":[62,184],"neural":[63],"under":[65],"a":[66,75,104,140,158],"shared":[67],"template:":[69],"compressing":[70],"high-dimensional":[71],"pointwise":[72],"features":[73],"into":[74],"compact":[76],"latent":[77],"space,":[78],"processing":[79],"interactions":[81],"within":[82],"it,":[83],"reconstructing":[85],"context":[88],"back":[89],"points.":[92],"Guided":[93],"view,":[96],"we":[97],"introduce":[98],"Low-Rank":[99],"Spatial":[100],"Attention":[101],"(LRSA)":[102],"clean":[105],"direct":[107],"instantiation":[108],"of":[109,172],"template.":[111],"Crucially,":[112],"unlike":[113],"prior":[114],"approaches":[115],"often":[117],"rely":[118],"non-standard":[120],"aggregation":[121],"or":[122],"normalization":[123],"modules,":[124],"LRSA":[125],"is":[126,144,161],"built":[127],"purely":[128],"from":[129],"standard":[130],"Transformer":[131],"primitives,":[132],"i.e.,":[133],"attention,":[134],"normalization,":[135],"feed-forward":[137],"networks,":[138],"yielding":[139,167],"concise":[141],"block":[142],"straightforward":[145],"implement":[147],"directly":[149],"compatible":[150],"with":[151],"hardware-optimized":[152],"kernels.":[153],"our":[155],"experiments,":[156],"such":[157],"simple":[159],"construction":[160],"sufficient":[162],"achieve":[164],"high":[165],"accuracy,":[166],"an":[168],"average":[169],"error":[170],"reduction":[171],"over":[173],"17\\%":[174],"relative":[175],"second-best":[177],"methods,":[178],"while":[179],"remaining":[180],"stable":[181],"efficient":[183],"mixed-precision":[185],"training.":[186]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-08T00:00:00"}