{"id":"https://openalex.org/W7161556155","doi":"https://doi.org/10.48550/arxiv.2605.15901","title":"From Layers to Networks: Comparing Neural Representations via Diffusion Geometry","display_name":"From Layers to Networks: Comparing Neural Representations via Diffusion Geometry","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161556155","doi":"https://doi.org/10.48550/arxiv.2605.15901"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15901","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15901","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.2605.15901","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136438053","display_name":"Atharva Khandait","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khandait, Atharva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136427696","display_name":"Jan E. Gerken","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerken, Jan E.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.3785000145435333,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.3785000145435333,"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":0.14319999516010284,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.09560000151395798,"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/markov-chain","display_name":"Markov chain","score":0.6054999828338623},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5568000078201294},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4715999960899353},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.46070000529289246},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.4562999904155731},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4377000033855438},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4374000132083893},{"id":"https://openalex.org/keywords/similitude","display_name":"Similitude","score":0.4142000079154968},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.40389999747276306}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5881999731063843},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5568000078201294},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.49959999322891235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49320000410079956},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4374000132083893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.40130001306533813},{"id":"https://openalex.org/C49555168","wikidata":"https://www.wikidata.org/wiki/Q176583","display_name":"Stochastic matrix","level":3,"score":0.3991999924182892},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38370001316070557},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2778045648","wikidata":"https://www.wikidata.org/wiki/Q176827","display_name":"Markov random field","level":4,"score":0.32589998841285706},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C192939610","wikidata":"https://www.wikidata.org/wiki/Q188444","display_name":"Differential geometry","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C109546454","wikidata":"https://www.wikidata.org/wiki/Q3798604","display_name":"Information geometry","level":4,"score":0.27230000495910645},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15901","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15901","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.2605.15901","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15901","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":{"Diffusion":[0],"geometry":[1,19,29,111],"is":[2,49],"a":[3,21,51,64,83,136],"manifold":[4],"learning":[5,37],"framework":[6],"that":[7,50,139],"uses":[8],"random":[9],"walks":[10],"defined":[11],"by":[12],"Markov":[13,72,127],"transition":[14,105],"matrices":[15,61,128],"to":[16,77,107,148,160],"characterize":[17],"the":[18,42,75,99,103,109,126,141,156,171],"of":[20,54,70,90,102,121,129],"dataset":[22],"at":[23,112],"multiple":[24,152],"scales.":[25,115],"We":[26,162,206],"use":[27],"diffusion":[28,80,114,134],"for":[30,41,197],"neural":[31],"representations,":[32],"incorporating":[33],"tools":[34],"from":[35,79,158],"multi-view":[36],"into":[38,135],"this":[39],"field":[40],"first":[43,84],"time.":[44],"Our":[45,187],"key":[46],"technical":[47],"observation":[48],"broad":[52],"class":[53],"similarity":[55,60,147],"measures":[56,123,169],"based":[57],"on":[58,170,180,211,216],"representational":[59],"(RSMs)":[62],"admits":[63],"closed-form":[65],"equivalent":[66],"formulation":[67],"in":[68,192],"terms":[69],"row-stochastic":[71],"matrices,":[73],"opening":[74],"door":[76],"manipulations":[78],"geometry.":[81],"As":[82],"application,":[85],"we":[86,118],"develop":[87],"multi-scale":[88],"variants":[89,120],"Centered":[91],"Kernel":[92],"Alignment":[93],"and":[94,154,194,200],"Distance":[95],"Correlation,":[96],"which":[97,124],"utilise":[98],"$t^{th}$":[100],"power":[101],"underlying":[104],"matrix":[106],"probe":[108],"data":[110],"adjustable":[113],"Going":[116],"further,":[117],"introduce":[119],"these":[122],"fuse":[125],"several":[130],"layers":[131,153],"via":[132],"alternating":[133],"single":[137],"operator":[138],"captures":[140],"network's":[142],"joint":[143],"sample":[144],"geometry,":[145],"allowing":[146],"be":[149],"computed":[150],"across":[151,183,203],"shifting":[155],"comparison":[157],"layer-to-layer":[159],"network-to-network.":[161],"perform":[163],"extensive":[164],"numerical":[165],"experiments,":[166],"evaluating":[167,215],"our":[168],"Representational":[172],"Similarity":[173],"(ReSi)":[174],"benchmark":[175,214],"comprising":[176],"14":[177],"architectures":[178],"trained":[179],"7":[181],"datasets":[182],"three":[184],"different":[185,204],"domains.":[186],"methods":[188],"achieve":[189],"SoTA":[190,209],"results":[191],"accuracy":[193],"output":[195],"correlation":[196],"both":[198],"language":[199],"vision":[201],"tasks":[202],"models.":[205],"furthermore":[207],"show":[208],"performance":[210],"an":[212],"additional":[213],"out-of-distribution":[217],"data.":[218]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-19T00:00:00"}