{"id":"https://openalex.org/W3207377002","doi":"https://doi.org/10.1109/icassp43922.2022.9747848","title":"Mixture Model Auto-Encoders: Deep Clustering Through Dictionary Learning","display_name":"Mixture Model Auto-Encoders: Deep Clustering Through Dictionary Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207377002","doi":"https://doi.org/10.1109/icassp43922.2022.9747848","mag":"3207377002"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747848","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080027674","display_name":"Alexander Lin","orcid":"https://orcid.org/0000-0002-3490-0301"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Lin","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences,Boston,MA,USA","School of Engineering and Applied Sciences, Harvard University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences,Boston,MA,USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066569995","display_name":"Andrew H. Song","orcid":"https://orcid.org/0000-0001-9356-9156"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew H. Song","raw_affiliation_strings":["Massachusetts Institute of Technology,Cambridge,MA,USA","Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Cambridge,MA,USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002643771","display_name":"Demba Ba","orcid":"https://orcid.org/0000-0002-1139-1030"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Demba Ba","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences,Boston,MA,USA","School of Engineering and Applied Sciences, Harvard University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences,Boston,MA,USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":null,"first_page":"3368","last_page":"3372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9970999956130981,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9957000017166138,"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/T11309","display_name":"Music and Audio Processing","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/interpretability","display_name":"Interpretability","score":0.826994776725769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774649977684021},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7637357711791992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6841917037963867},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6444025635719299},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6197918057441711},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5584039092063904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5505393743515015},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4853145480155945},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.47912096977233887},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43530458211898804},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43347224593162537},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35528284311294556},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32441389560699463},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2811856269836426}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.826994776725769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774649977684021},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7637357711791992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6841917037963867},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6444025635719299},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6197918057441711},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5584039092063904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5505393743515015},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4853145480155945},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.47912096977233887},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43530458211898804},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43347224593162537},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35528284311294556},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32441389560699463},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2811856269836426},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747848","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1993962865","https://openalex.org/W2049633694","https://openalex.org/W2100556411","https://openalex.org/W2100659887","https://openalex.org/W2115706991","https://openalex.org/W2118103795","https://openalex.org/W2150884987","https://openalex.org/W2160547390","https://openalex.org/W2533545350","https://openalex.org/W2750384547","https://openalex.org/W2773850766","https://openalex.org/W2912027531","https://openalex.org/W2923099764","https://openalex.org/W2963372528","https://openalex.org/W2963403868","https://openalex.org/W2964074409","https://openalex.org/W2964121744","https://openalex.org/W2993554215","https://openalex.org/W3015476709","https://openalex.org/W3035162526","https://openalex.org/W3045150439","https://openalex.org/W3100730608","https://openalex.org/W3112170415","https://openalex.org/W3129341902","https://openalex.org/W3131466454","https://openalex.org/W3151214789","https://openalex.org/W3169439816","https://openalex.org/W4238056994","https://openalex.org/W4295677899","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6677645113","https://openalex.org/W6685380521","https://openalex.org/W6728550200","https://openalex.org/W6739901393","https://openalex.org/W6743688258","https://openalex.org/W6758705071","https://openalex.org/W6769191023","https://openalex.org/W6775511469","https://openalex.org/W6787161265","https://openalex.org/W6790709309","https://openalex.org/W6790880238","https://openalex.org/W6793978120","https://openalex.org/W6796817738"],"related_works":["https://openalex.org/W3006943036","https://openalex.org/W4299487748","https://openalex.org/W3123344745","https://openalex.org/W2784313445","https://openalex.org/W2292254049","https://openalex.org/W4310034804","https://openalex.org/W3217300629","https://openalex.org/W2592385986","https://openalex.org/W4312783963","https://openalex.org/W4302303815"],"abstract_inverted_index":{"State-of-the-art":[0],"approaches":[1],"for":[2],"clustering":[3,100],"high-dimensional":[4],"data":[5,46,72],"utilize":[6],"deep":[7,99],"auto-encoder":[8],"architectures.":[9],"Many":[10],"of":[11,18,25,32,105],"these":[12],"networks":[13],"require":[14],"a":[15,23,41,51,74],"large":[16],"number":[17],"parameters":[19],"and":[20,61],"suffer":[21],"from":[22,57],"lack":[24],"interpretability,":[26],"due":[27],"to":[28],"the":[29,33,81],"black-box":[30],"nature":[31],"auto-encoders.":[34],"We":[35],"introduce":[36],"Mixture":[37],"Model":[38],"Auto-Encoders":[39],"(MixMate),":[40],"novel":[42],"architecture":[43],"that":[44,92],"clusters":[45],"by":[47],"performing":[48],"inference":[49],"on":[50,55,86],"generative":[52],"model.":[53],"Built":[54],"ideas":[56],"sparse":[58],"dictionary":[59],"learning":[60],"mixture":[62],"models,":[63],"MixMate":[64,93],"comprises":[65],"several":[66],"auto-encoders,":[67],"each":[68],"tasked":[69],"with":[70],"reconstructing":[71],"in":[73,80],"distinct":[75],"cluster,":[76],"while":[77,102],"enforcing":[78],"sparsity":[79],"latent":[82],"space.":[83],"Through":[84],"experiments":[85],"various":[87],"image":[88],"datasets,":[89],"we":[90],"show":[91],"achieves":[94],"competitive":[95],"performance":[96],"versus":[97],"state-of-the-art":[98],"algorithms,":[101],"using":[103],"orders":[104],"magnitude":[106],"fewer":[107],"parameters.":[108]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}