{"id":"https://openalex.org/W7152557129","doi":"https://doi.org/10.1145/3774904.3792528","title":"Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning","display_name":"Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152557129","doi":"https://doi.org/10.1145/3774904.3792528"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792528","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792528","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792528","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009956478","display_name":"Jinjin Guo","orcid":"https://orcid.org/0000-0002-6801-4471"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinjin Guo","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6801-4471","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yexin Li","orcid":"https://orcid.org/0000-0001-5907-8978"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yexin Li","raw_affiliation_strings":["State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5907-8978","affiliations":[{"raw_affiliation_string":"State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101547686","display_name":"Zhichao Huang","orcid":"https://orcid.org/0000-0002-7662-5184"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Huang","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7662-5184","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133262386","display_name":"Jun Fang","orcid":"https://orcid.org/0009-0003-9389-6618"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Fang","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-9389-6618","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133301939","display_name":"Zhiyuan Liu","orcid":"https://orcid.org/0009-0000-8508-444X"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Liu","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8508-444X","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Liu","orcid":"https://orcid.org/0009-0003-9104-1587"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Liu","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-9104-1587","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054904119","display_name":"Pengzhang Liu","orcid":"https://orcid.org/0000-0002-6031-5245"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengzhang Liu","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6031-5245","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133263264","display_name":"Qixia Jiang","orcid":"https://orcid.org/0009-0006-1465-041X"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixia Jiang","raw_affiliation_strings":["JD.com, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1465-041X","affiliations":[{"raw_affiliation_string":"JD.com, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50732699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4127","last_page":"4136"},"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":0.5094000101089478,"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":0.5094000101089478,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1200999990105629,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11509999632835388,"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/representation","display_name":"Representation (politics)","score":0.49410000443458557},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3603000044822693},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3506999909877777},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.30079999566078186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5666000247001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5467000007629395},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49410000443458557},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30329999327659607},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24729999899864197}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792528","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792528","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792528","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792528","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7871270179748535,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2060581589","https://openalex.org/W2138621090","https://openalex.org/W3185250692"],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"multimodal":[1,191,217],"contrastive":[2,160,210],"learning":[3,10],"has":[4],"recently":[5],"achieved":[6],"impressive":[7],"success":[8],"in":[9,54,166],"rich":[11],"and":[12,27,67,73,82,99,127,170,181,200],"transferable":[13],"representations,":[14],"yet":[15],"it":[16],"remains":[17],"fundamentally":[18],"limited":[19],"by":[20,65],"the":[21,28,31,36,59,90,93,96,152,168,178],"uniform":[22],"treatment":[23],"of":[24,30,35,61,95],"feature":[25,112,169],"dimensions":[26,62,113],"neglect":[29],"intrinsic":[32],"spectral":[33,71,101,134,171,175],"structure":[34],"learned":[37],"features.":[38],"Empirical":[39],"evidence":[40],"indicates":[41],"that":[42,88,117,123,162,194],"high-dimensional":[43],"embeddings":[44],"tend":[45],"to":[46,109],"collapse":[47],"into":[48,114,177],"narrow":[49],"cones,":[50],"concentrating":[51],"task-relevant":[52],"semantics":[53],"a":[55,85,158],"small":[56],"subspace,":[57],"while":[58],"majority":[60],"remain":[63],"occupied":[64],"noise":[66,128],"spurious":[68],"correlations.":[69],"Such":[70],"imbalance":[72],"entanglement":[74],"undermine":[75],"model":[76],"generalization.":[77],"We":[78],"propose":[79],"Spectral":[80],"Disentanglement":[81],"Enhancement":[83],"(SDE),":[84],"novel":[86],"framework":[87],"bridges":[89],"gap":[91],"between":[92],"geometry":[94],"embedded":[97],"spaces":[98],"their":[100],"properties.":[102],"Our":[103],"approach":[104],"leverages":[105],"singular":[106],"value":[107],"decomposition":[108],"adaptively":[110],"partition":[111],"strong":[115],"signals":[116,122],"capture":[118],"task-critical":[119],"semantics,":[120],"weak":[121],"reflect":[124],"ancillary":[125],"correlations,":[126],"representing":[129],"irrelevant":[130],"perturbations.":[131],"A":[132],"curriculum-based":[133],"enhancement":[135],"strategy":[136],"is":[137],"then":[138],"applied,":[139],"selectively":[140],"amplifying":[141],"informative":[142],"components":[143],"with":[144,208],"theoretical":[145],"guarantees":[146],"on":[147,189],"training":[148,179],"stability.":[149],"Building":[150],"upon":[151],"enhanced":[153],"features,":[154],"we":[155],"further":[156],"introduce":[157],"dual-domain":[159],"loss":[161],"jointly":[163],"optimizes":[164],"alignment":[165],"both":[167],"spaces,":[172],"effectively":[173],"integrating":[174],"regularization":[176],"process":[180],"encouraging":[182],"richer,":[183],"more":[184],"robust":[185],"representations.":[186],"Extensive":[187],"experiments":[188],"large-scale":[190],"benchmarks":[192],"demonstrate":[193],"SDE":[195,205],"consistently":[196],"improves":[197],"representation":[198,218],"robustness":[199],"generalization,":[201],"outperforming":[202],"state-of-the-art":[203],"methods.":[204],"integrates":[206],"seamlessly":[207],"existing":[209],"pipelines,":[211],"offering":[212],"an":[213],"effective":[214],"solution":[215],"for":[216],"learning.":[219]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}