{"id":"https://openalex.org/W7163003368","doi":"https://doi.org/10.48550/arxiv.2605.31559","title":"Functional Attention: From Pairwise Affinities to Functional Correspondences","display_name":"Functional Attention: From Pairwise Affinities to Functional Correspondences","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163003368","doi":"https://doi.org/10.48550/arxiv.2605.31559"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.31559","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31559","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.2605.31559","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137573213","display_name":"Jiefang Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Jiefang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022094171","display_name":"Maolin Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Maolin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137595926","display_name":"Simon Weber","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weber, Simon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005070305","display_name":"Guandao Yang","orcid":"https://orcid.org/0000-0002-2992-5803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Guandao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137599206","display_name":"Daniel Cremers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cremers, Daniel","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":0.2087000012397766,"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":0.2087000012397766,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.1362999975681305,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.11389999836683273,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7250999808311462},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.6003000140190125},{"id":"https://openalex.org/keywords/affinities","display_name":"Affinities","score":0.5403000116348267},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5403000116348267},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44130000472068787},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43700000643730164}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7250999808311462},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.6003000140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5694000124931335},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C2780283098","wikidata":"https://www.wikidata.org/wiki/Q4688960","display_name":"Affinities","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4821000099182129},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44130000472068787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4399999976158142},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C55112680","wikidata":"https://www.wikidata.org/wiki/Q190549","display_name":"Functional analysis","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C71176878","wikidata":"https://www.wikidata.org/wiki/Q17014987","display_name":"Functional principal component analysis","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.31559","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31559","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.2605.31559","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31559","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0],"mappings":[1],"between":[2,53],"infinite-dimensional":[3],"function":[4],"spaces,":[5],"or":[6],"operator":[7,93],"learning,":[8],"is":[9,111],"essential":[10],"for":[11],"many":[12,92],"machine":[13],"learning":[14,94],"applications.":[15],"Although":[16],"transformer-based":[17],"operators":[18],"are":[19],"popular,":[20],"they":[21],"often":[22],"rely":[23],"on":[24],"token-wise":[25],"attention.":[26],"These":[27],"methods":[28],"treat":[29],"continuous":[30],"fields":[31],"as":[32,49],"discrete":[33],"tokens":[34],"and":[35,101],"usually":[36],"ignore":[37],"the":[38],"global":[39,80],"functional":[40,51,59],"structure.":[41],"We":[42],"introduce":[43],"\\emph{Functional":[44,85],"Attention},":[45],"which":[46],"reinterprets":[47],"attention":[48],"a":[50,72],"correspondence":[52],"adaptive":[54],"bases.":[55],"Inspired":[56],"by":[57],"geometric":[58],"maps,":[60],"our":[61],"method":[62],"replaces":[63],"softmax":[64],"affinities":[65],"with":[66],"structured":[67],"linear":[68],"operators.":[69],"This":[70],"yields":[71],"compact,":[73],"generalizable,":[74],"resolution-invariant":[75],"representation":[76],"that":[77,84],"explicitly":[78],"captures":[79],"dependencies.":[81],"Experiments":[82],"demonstrate":[83],"Attention}":[86],"can":[87],"match":[88],"state-of-the-art":[89],"performance":[90],"in":[91],"tasks,":[95],"including":[96],"solving":[97],"PDEs,":[98],"3D":[99],"segmentation,":[100],"regression,":[102],"while":[103],"remaining":[104],"robust":[105],"to":[106],"varying":[107],"discretizations.":[108],"Project":[109],"page":[110],"available":[112],"at":[113],"https://github.com/xjffff/FUNCATTN.":[114]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-02T00:00:00"}