{"id":"https://openalex.org/W7141412622","doi":"https://doi.org/10.48550/arxiv.2603.25083","title":"Learning domain-invariant features through channel-level sparsification for Out-Of Distribution Generalization","display_name":"Learning domain-invariant features through channel-level sparsification for Out-Of Distribution Generalization","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141412622","doi":"https://doi.org/10.48550/arxiv.2603.25083"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25083","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":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.2603.25083","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130761439","display_name":"Haoran Pei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130725019","display_name":"Yuguang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yuguang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130812129","display_name":"Kexin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Kexin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130778338","display_name":"Juan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Juan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130788967","display_name":"Baochang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Baochang","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":0.6769999861717224,"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":0.6769999861717224,"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":0.08370000123977661,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.07940000295639038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7092999815940857},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6152999997138977},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5809000134468079},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.574400007724762},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5715000033378601},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5403000116348267},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5300999879837036},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.48179998993873596},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4366999864578247}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7092999815940857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6284999847412109},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5809000134468079},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.574400007724762},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5403000116348267},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5192000269889832},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C38764148","wikidata":"https://www.wikidata.org/wiki/Q17098245","display_name":"Interaction information","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25083","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":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.2603.25083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25083","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":null,"license_id":null,"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":{"Out-of-Distribution":[0],"(OOD)":[1],"generalization":[2],"has":[3],"become":[4],"a":[5,80,105,117,147],"primary":[6],"metric":[7],"for":[8],"evaluating":[9],"image":[10],"analysis":[11],"systems.":[12],"Since":[13],"deep":[14,58],"learning":[15,70],"models":[16],"tend":[17],"to":[18,32,46,52,87,96,123],"capture":[19],"domain-specific":[20],"context,":[21],"they":[22,50],"often":[23],"develop":[24],"shortcut":[25,69],"dependencies":[26],"on":[27,164],"these":[28],"non-causal":[29],"features,":[30],"leading":[31],"inconsistent":[33],"performance":[34],"across":[35],"different":[36],"data":[37],"sources.":[38],"Current":[39],"techniques,":[40],"such":[41],"as":[42],"invariance":[43],"learning,":[44],"attempt":[45],"mitigate":[47],"this.":[48],"However,":[49],"struggle":[51],"isolate":[53],"highly":[54],"mixed":[55],"features":[56,99,130],"within":[57],"latent":[59,129],"spaces.":[60],"This":[61,91],"limitation":[62],"prevents":[63,152],"them":[64],"from":[65,100,155],"fully":[66],"resolving":[67],"the":[68,94,109,125,137,153],"problem.In":[71],"this":[72],"paper,":[73],"we":[74,145],"propose":[75],"Hierarchical":[76],"Causal":[77],"Dropout":[78],"(HCD),":[79],"method":[81],"that":[82,168],"uses":[83],"channel-level":[84],"causal":[85,98,106,160],"masks":[86,154],"enforce":[88],"feature":[89],"sparsity.":[90],"approach":[92],"allows":[93],"model":[95],"separate":[97],"spurious":[101],"ones,":[102],"effectively":[103],"performing":[104],"intervention":[107],"at":[108],"representation":[110],"level.":[111],"The":[112],"training":[113],"is":[114],"guided":[115],"by":[116],"Matrix-based":[118],"Mutual":[119],"Information":[120],"(MMI)":[121],"objective":[122],"minimize":[124],"mutual":[126],"information":[127,138],"between":[128],"and":[131],"domain":[132],"labels,":[133],"while":[134],"simultaneously":[135],"maximizing":[136],"shared":[139],"with":[140],"class":[141],"labels.To":[142],"ensure":[143],"stability,":[144],"incorporate":[146],"StyleMix-driven":[148],"VICReg":[149],"module,":[150],"which":[151],"accidentally":[156],"filtering":[157],"out":[158],"essential":[159],"data.":[161],"Experimental":[162],"results":[163],"OOD":[165],"benchmarks":[166],"show":[167],"HCD":[169],"performs":[170],"better":[171],"than":[172],"existing":[173],"top-tier":[174],"methods.":[175]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-28T00:00:00"}