{"id":"https://openalex.org/W7131403221","doi":"https://doi.org/10.48550/arxiv.2602.19331","title":"Partial Soft-Matching Distance for Neural Representational Comparison with Partial Unit Correspondence","display_name":"Partial Soft-Matching Distance for Neural Representational Comparison with Partial Unit Correspondence","publication_year":2026,"publication_date":"2026-02-22","ids":{"openalex":"https://openalex.org/W7131403221","doi":"https://doi.org/10.48550/arxiv.2602.19331"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.19331","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19331","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.19331","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090373327","display_name":"Chandni Kapoor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kapoor, Chaitanya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126846748","display_name":"Alex H. Williams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Williams, Alex H.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050983647","display_name":"Meenakshi Khosla","orcid":"https://orcid.org/0000-0002-2910-6242"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khosla, Meenakshi","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/T11094","display_name":"Face Recognition and Perception","score":0.5845000147819519,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.5845000147819519,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.19850000739097595,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.029200000688433647,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7142999768257141},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.5906999707221985},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5332000255584717},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4765999913215637},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4507000148296356},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4271000027656555},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.40630000829696655}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7142999768257141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797000169754028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6209999918937683},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48579999804496765},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4271000027656555},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38999998569488525},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C3004257","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Correspondence problem","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26179999113082886},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.19331","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19331","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.19331","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19331","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.5208315253257751,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Representational":[0],"similarity":[1],"metrics":[2],"typically":[3],"force":[4],"all":[5,135],"units":[6,136,145,153],"to":[7,13,26,36,133,159],"be":[8],"matched,":[9],"making":[10],"them":[11],"susceptible":[12],"noise":[14],"and":[15,62,86,104,186],"outliers":[16,85],"common":[17],"in":[18,69,92],"neural":[19],"representations.":[20],"We":[21],"extend":[22],"the":[23,89],"soft-matching":[24,46,182],"distance":[25,47],"a":[27,184],"partial":[28,45,181,193],"optimal":[29],"transport":[30,59],"setting":[31],"that":[32,111],"allows":[33],"some":[34],"neurons":[35],"remain":[37],"unmatched,":[38],"yielding":[39],"rotation-sensitive":[40],"but":[41],"robust":[42],"correspondences.":[43],"This":[44,157],"provides":[48,183],"theoretical":[49],"advantages":[50],"--":[51,61],"relaxing":[52],"strict":[53],"mass":[54],"conservation":[55],"while":[56,151],"maintaining":[57],"interpretable":[58],"costs":[60],"practical":[63,187],"benefits":[64],"through":[65],"efficient":[66],"neuron":[67],"ranking":[68],"terms":[70],"of":[71,138],"cross-network":[72],"alignment":[73,109,121],"without":[74],"costly":[75],"iterative":[76],"recomputation.":[77],"In":[78,140],"simulations,":[79],"it":[80,99],"preserves":[81],"correct":[82,90],"matches":[83],"under":[84,192],"reliably":[87],"selects":[88],"model":[91],"noise-corrupted":[93],"identification":[94],"tasks.":[95],"On":[96],"fMRI":[97],"data,":[98],"automatically":[100],"excludes":[101],"low-reliability":[102],"voxels":[103],"produces":[105],"voxel":[106],"rankings":[107],"by":[108,161],"quality":[110,163],"closely":[112],"match":[113,134,162],"computationally":[114],"expensive":[115],"brute-force":[116],"approaches.":[117],"It":[118],"achieves":[119],"higher":[120],"precision":[122],"across":[123],"homologous":[124],"brain":[125],"areas":[126],"than":[127],"standard":[128],"soft-matching,":[129],"which":[130],"is":[131],"forced":[132],"regardless":[137],"quality.":[139],"deep":[141],"networks,":[142],"highly":[143],"matched":[144],"exhibit":[146],"similar":[147],"maximally":[148],"exciting":[149],"images,":[150],"unmatched":[152],"show":[154],"divergent":[155],"patterns.":[156],"ability":[158],"partition":[160],"enables":[164],"focused":[165],"analyses,":[166],"e.g.,":[167],"testing":[168],"whether":[169],"networks":[170],"have":[171],"privileged":[172],"axes":[173],"even":[174],"within":[175],"their":[176],"most":[177],"aligned":[178],"subpopulations.":[179],"Overall,":[180],"principled":[185],"method":[188],"for":[189],"representational":[190],"comparison":[191],"correspondence.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-26T00:00:00"}