{"id":"https://openalex.org/W4415535649","doi":"https://doi.org/10.1145/3746027.3755540","title":"FITMM: Adaptive Frequency-Aware Multimodal Recommendation via Information-Theoretic Representation Learning","display_name":"FITMM: Adaptive Frequency-Aware Multimodal Recommendation via Information-Theoretic Representation Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415535649","doi":"https://doi.org/10.1145/3746027.3755540"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042361412","display_name":"Wei Yang","orcid":"https://orcid.org/0009-0004-0151-2160"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0151-2160","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110336338","display_name":"Rui Zhong","orcid":"https://orcid.org/0009-0004-0704-015X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhong","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0704-015X","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013838158","display_name":"Yiqun Chen","orcid":"https://orcid.org/0009-0008-6135-2604"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6135-2604","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shixuan Li","orcid":"https://orcid.org/0009-0005-0481-556X"},"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":"Shixuan Li","raw_affiliation_strings":["University of Southern California, Los Angeles, California, USA"],"raw_orcid":"https://orcid.org/0009-0005-0481-556X","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011759850","display_name":"Heng Ping","orcid":null},"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":"Heng Ping","raw_affiliation_strings":["University of Southern California, Los Angeles, California, USA"],"raw_orcid":"https://orcid.org/0009-0008-8127-3401","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108692383","display_name":"Chi Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Lu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1478-0697","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001339397","display_name":"Peng Jiang","orcid":"https://orcid.org/0000-0002-9266-0780"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jiang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9266-0780","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0156,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92398702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6193","last_page":"6202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.5929999947547913},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5835000276565552},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5162000060081482},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.510699987411499},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49869999289512634},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4546000063419342},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4390000104904175},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.39320001006126404},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3763999938964844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480999827384949},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5929999947547913},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5835000276565552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49869999289512634},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.36579999327659607},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:doi:10.48550/arxiv.2601.22498","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2601.22498","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","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":43,"referenced_works":["https://openalex.org/W1991252559","https://openalex.org/W2046234722","https://openalex.org/W2054141820","https://openalex.org/W2103406330","https://openalex.org/W2113131123","https://openalex.org/W2158787690","https://openalex.org/W2796431263","https://openalex.org/W2910589063","https://openalex.org/W2963655167","https://openalex.org/W2963900085","https://openalex.org/W2964258748","https://openalex.org/W2982108874","https://openalex.org/W3024534448","https://openalex.org/W3045200674","https://openalex.org/W3080642298","https://openalex.org/W3091129453","https://openalex.org/W3093002391","https://openalex.org/W3094605801","https://openalex.org/W3192113933","https://openalex.org/W3199763349","https://openalex.org/W4205091644","https://openalex.org/W4224326485","https://openalex.org/W4285288414","https://openalex.org/W4304014904","https://openalex.org/W4309185982","https://openalex.org/W4310631727","https://openalex.org/W4321485450","https://openalex.org/W4322718576","https://openalex.org/W4327808327","https://openalex.org/W4384655737","https://openalex.org/W4387171276","https://openalex.org/W4387379288","https://openalex.org/W4387848785","https://openalex.org/W4390451911","https://openalex.org/W4393159797","https://openalex.org/W4396736150","https://openalex.org/W4399114772","https://openalex.org/W4400351882","https://openalex.org/W4401863256","https://openalex.org/W4403221702","https://openalex.org/W4403577865","https://openalex.org/W4403791575","https://openalex.org/W4409365832"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"recommendation":[1,163],"aims":[2],"to":[3,95],"enhance":[4],"user":[5],"preference":[6],"modeling":[7],"by":[8],"leveraging":[9],"rich":[10],"item":[11,89],"content":[12],"such":[13],"as":[14],"images":[15],"and":[16,33,36,44,99,118,175],"text.":[17],"Yet":[18],"dominant":[19],"systems":[20],"fuse":[21],"modalities":[22,151],"in":[23],"the":[24,28,56,112,161],"spatial":[25],"domain,":[26],"obscuring":[27],"frequency":[29,63],"structure":[30],"of":[31,138],"signals":[32],"amplifying":[34],"misalignment":[35],"redundancy.":[37],"We":[38,141],"adopt":[39],"a":[40,66,79,125,144],"spectral":[41,93,146],"information-theoretic":[42],"view":[43],"show":[45],"that,":[46],"under":[47],"an":[48],"orthogonal":[49,97],"transform":[50],"that":[51,129,149,172],"approximately":[52],"block-diagonalizes":[53],"bandwise":[54],"covariances,":[55],"Gaussian":[57],"Information":[58],"Bottleneck":[59],"objective":[60],"decouples":[61],"across":[62,132],"bands,":[64,98],"providing":[65],"principled":[67],"basis":[68],"for":[69,83],"separate-then-fuse":[70],"paradigm.":[71],"Building":[72],"on":[73,167],"this":[74],"foundation,":[75],"we":[76,121],"propose":[77],"FITMM,":[78],"Frequency-aware":[80],"Information-Theoretic":[81],"framework":[82],"multimodal":[84,103],"recommendation.":[85],"FITMM":[86,173],"constructs":[87],"graph-enhanced":[88],"representations,":[90],"performs":[91],"modality-wise":[92],"decomposition":[94],"obtain":[96],"forms":[100],"lightweight":[101],"within-band":[102],"components.":[104],"A":[105],"residual,":[106],"task-adaptive":[107],"gate":[108],"aggregates":[109],"bands":[110,133],"into":[111],"final":[113],"representation.":[114],"To":[115],"control":[116],"redundancy":[117],"improve":[119],"generalization,":[120],"regularize":[122],"training":[123],"with":[124,136,160],"frequency-domain":[126],"IB":[127],"term":[128],"allocates":[130],"capacity":[131],"(Wiener-like":[134],"shrinkage":[135],"shut-off":[137],"weak":[139],"bands).":[140],"further":[142],"introduce":[143],"cross-modal":[145],"consistency":[147],"loss":[148],"aligns":[150],"within":[152],"each":[153],"band.":[154],"The":[155],"model":[156],"is":[157],"jointly":[158],"optimized":[159],"standard":[162],"loss.":[164],"Extensive":[165],"experiments":[166],"three":[168],"real-world":[169],"datasets":[170],"demonstrate":[171],"consistently":[174],"significantly":[176],"outperforms":[177],"advanced":[178],"baselines.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}