{"id":"https://openalex.org/W4282027013","doi":"https://doi.org/10.1145/3534678.3539438","title":"Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation","display_name":"Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4282027013","doi":"https://doi.org/10.1145/3534678.3539438"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539438","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539438","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539438","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539438","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101892837","display_name":"Haohan Wang","orcid":"https://orcid.org/0000-0002-1826-4069"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haohan Wang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077288556","display_name":"Zeyi Huang","orcid":"https://orcid.org/0009-0009-3221-2597"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyi Huang","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, PA, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017086686","display_name":"Xindi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xindi Wu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Xing","raw_affiliation_strings":["MUZUAI, Carnegie Mellon University, & Petuum Inc., Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"MUZUAI, Carnegie Mellon University, & Petuum Inc., Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101892837"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.5218,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.62019078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1846","last_page":"1856"},"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":0.9973000288009644,"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":0.9973000288009644,"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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9742000102996826,"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/regularization","display_name":"Regularization (linguistics)","score":0.756710410118103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6360999345779419},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5466079115867615},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5415878295898438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4988720417022705},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4349225163459778},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.42392027378082275},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4195915162563324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3950619399547577},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33118924498558044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2516290545463562},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09620353579521179}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.756710410118103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6360999345779419},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5466079115867615},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5415878295898438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4988720417022705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4349225163459778},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.42392027378082275},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4195915162563324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3950619399547577},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33118924498558044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2516290545463562},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09620353579521179},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539438","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539438","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539438","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3534678.3539438","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539438","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539438","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G1171700966","display_name":null,"funder_award_id":"NSF CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1491865986","display_name":"CAREER: Weakly-Supervised Visual Scene Understanding: Combining Images and Videos, and Going Beyond Semantic Tags","funder_award_id":"2150012","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G264567485","display_name":"III: Small: A New Approach to Latent Space Learning with Diversity-Inducing Regularization and Applications to Healthcare Data Analytics","funder_award_id":"1617583","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3611247453","display_name":null,"funder_award_id":"R01GM","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6182358478","display_name":null,"funder_award_id":"IIS1617583","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6347617425","display_name":null,"funder_award_id":"P30DA035778","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8222509937","display_name":null,"funder_award_id":"R01GM114311,P30DA035778","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8288036582","display_name":null,"funder_award_id":"NIH R01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8559643739","display_name":null,"funder_award_id":"R01GM114311","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8891651847","display_name":null,"funder_award_id":"IIS1617583,IIS-2150012,IIS-2204808","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4282027013.pdf","grobid_xml":"https://content.openalex.org/works/W4282027013.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W385466589","https://openalex.org/W1585160083","https://openalex.org/W1929903369","https://openalex.org/W2015140204","https://openalex.org/W2112796928","https://openalex.org/W2342045095","https://openalex.org/W2460583509","https://openalex.org/W2560674852","https://openalex.org/W2683470288","https://openalex.org/W2747329762","https://openalex.org/W2885724687","https://openalex.org/W2886776719","https://openalex.org/W2949736877","https://openalex.org/W2954996726","https://openalex.org/W2988160852","https://openalex.org/W2998115938","https://openalex.org/W2998508940","https://openalex.org/W4288094577"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W4281727072","https://openalex.org/W2560201613","https://openalex.org/W3154990682","https://openalex.org/W2171975302","https://openalex.org/W2022352247","https://openalex.org/W1532073221","https://openalex.org/W2377538627","https://openalex.org/W2107220315","https://openalex.org/W1589637664"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,39,137],"has":[2],"been":[3],"proven":[4],"to":[5,18,40,48,52,70,99,117,172],"be":[6],"an":[7],"effective":[8],"technique":[9,33,132],"for":[10,86,170],"developing":[11],"machine":[12],"learning":[13],"models":[14],"that":[15,146],"are":[16],"robust":[17],"known":[19],"classes":[20],"of":[21,26,63,65,74,82,102,114,149,154,179],"distributional":[22],"shifts":[23,50],"(e.g.,":[24],"rotations":[25],"images),":[27],"and":[28,84,144,168],"alignment":[29,66,115,142],"regularization":[30,116],"is":[31],"a":[32,61,90,162,177],"often":[34],"used":[35,51],"together":[36],"with":[37,138,176],"data":[38,136],"further":[41],"help":[42],"the":[43,49,54,72,80,100,112,147,155,174],"model":[44],"learn":[45],"representations":[46],"invariant":[47],"augment":[53],"data.":[55],"In":[56],"this":[57,130,150],"paper,":[58],"motivated":[59],"by":[60],"proliferation":[62],"options":[64],"regularizations,":[67],"we":[68,88,108,124,128,133],"seek":[69],"evaluate":[71],"performances":[73],"several":[75],"popular":[76],"design":[77],"choices":[78],"along":[79],"dimensions":[81],"robustness":[83],"invariance,":[85],"which":[87],"introduce":[89],"new":[91],"test":[92,129],"procedure.":[93],"Our":[94],"synthetic":[95],"experiment":[96],"results":[97],"speak":[98],"benefits":[101,148],"squared":[103,139],"\u21132":[104,140],"norm":[105,141],"regularization.":[106],"Further,":[107],"also":[109,160],"formally":[110],"analyze":[111],"behavior":[113],"complement":[118],"our":[119],"empirical":[120],"study":[121],"under":[122],"assumptions":[123],"consider":[125],"realistic.":[126],"Finally,":[127],"simple":[131],"identify":[134],"(worst-case":[135],"regularization)":[143],"show":[145],"method":[151,175],"outrun":[152],"those":[153],"specially":[156],"designed":[157],"methods.":[158],"We":[159],"release":[161],"software":[163],"package":[164],"in":[165],"both":[166],"TensorFlow":[167],"PyTorch":[169],"users":[171],"use":[173],"couple":[178],"lines":[180],"at":[181],"https://github.com/jyanln/AlignReg.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}