{"id":"https://openalex.org/W4409117979","doi":"https://doi.org/10.1145/3712678.3721885","title":"ModalityMirror: Enhancing Audio Classification in Modality Heterogeneity Federated Learning via Multimodal Distillation","display_name":"ModalityMirror: Enhancing Audio Classification in Modality Heterogeneity Federated Learning via Multimodal Distillation","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4409117979","doi":"https://doi.org/10.1145/3712678.3721885"},"language":"en","primary_location":{"id":"doi:10.1145/3712678.3721885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712678.3721885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3712678.3721885","source":null,"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 35th edition of the Workshop on Network and Operating System Support for Digital Audio and Video","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3712678.3721885","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059679122","display_name":"Tiantian Feng","orcid":"https://orcid.org/0000-0002-2053-9068"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2053-9068","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029803129","display_name":"Tuo Zhang","orcid":"https://orcid.org/0000-0003-3676-0717"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuo Zhang","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3676-0717","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047191296","display_name":"A. Salman Avestimehr","orcid":"https://orcid.org/0000-0003-3102-0867"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Salman Avestimehr","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3102-0867","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1052-6204","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":4.5234,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94032039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8065648674964905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7550825476646423},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6889098286628723},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.37896353006362915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3755183815956116}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8065648674964905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7550825476646423},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6889098286628723},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.37896353006362915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3755183815956116},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712678.3721885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712678.3721885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3712678.3721885","source":null,"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 35th edition of the Workshop on Network and Operating System Support for Digital Audio and Video","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3712678.3721885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712678.3721885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3712678.3721885","source":null,"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 35th edition of the Workshop on Network and Operating System Support for Digital Audio and Video","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409117979.pdf","grobid_xml":"https://content.openalex.org/works/W4409117979.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2108598243","https://openalex.org/W2417336996","https://openalex.org/W3154807520","https://openalex.org/W3213321731","https://openalex.org/W4206936477","https://openalex.org/W4283367167","https://openalex.org/W4290877962","https://openalex.org/W4290945297","https://openalex.org/W4380926296","https://openalex.org/W4387105517","https://openalex.org/W4401856724"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Multimodal":[0],"Federated":[1],"Learning":[2],"frequently":[3],"encounters":[4],"challenges":[5],"of":[6],"client":[7],"modality":[8,16,36,124],"heterogeneity,":[9],"leading":[10],"to":[11,32,47,70,83,100],"undesired":[12],"performances":[13],"for":[14,120],"secondary":[15],"in":[17,24,37,109,127],"multimodal":[18,128],"learning.":[19],"It":[20],"is":[21,29],"particularly":[22,108],"prevalent":[23],"audiovisual":[25,58,110],"learning,":[26],"with":[27],"audio":[28,49,97],"often":[30],"assumed":[31],"be":[33],"the":[34,96,101,118,122],"weaker":[35],"recognition":[38],"tasks.":[39],"To":[40],"address":[41],"this":[42],"challenge,":[43],"we":[44],"introduce":[45],"ModalityMirror":[46,62,93],"improve":[48],"model":[50],"performance":[51],"by":[52],"leveraging":[53],"knowledge":[54,77],"distillation":[55,78],"from":[56],"an":[57],"federated":[59,76],"learning":[60],"model.":[61,88],"involves":[63],"two":[64],"phases:":[65],"a":[66,75,85],"modality-wise":[67],"FL":[68,103,111],"stage":[69,79],"aggregate":[71],"unimodal":[72,86],"encoders;":[73],"and":[74],"on":[80],"multimodality":[81],"clients":[82],"train":[84],"student":[87],"Our":[89,115],"results":[90],"demonstrate":[91],"that":[92],"significantly":[94],"improves":[95],"classification":[98],"compared":[99],"state-of-the-art":[102],"methods":[104],"such":[105],"as":[106],"Harmony,":[107],"facing":[112],"video":[113],"missing.":[114],"approach":[116],"unlocks":[117],"potential":[119],"exploiting":[121],"diverse":[123],"spectrum":[125],"inherent":[126],"FL.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}