{"id":"https://openalex.org/W4403791719","doi":"https://doi.org/10.1145/3664647.3681164","title":"Incremental Learning via Robust Parameter Posterior Fusion","display_name":"Incremental Learning via Robust Parameter Posterior Fusion","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791719","doi":"https://doi.org/10.1145/3664647.3681164"},"language":"es","primary_location":{"id":"doi:10.1145/3664647.3681164","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5075882217","display_name":"Wenju Sun","orcid":"https://orcid.org/0000-0002-0317-3922"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenju Sun","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005350496","display_name":"Qingyong Li","orcid":"https://orcid.org/0000-0002-3860-4809"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyong Li","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107934474","display_name":"Siyu Zhang","orcid":"https://orcid.org/0009-0003-8026-1402"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Zhang","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101515505","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0003-2898-3259"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102819696","display_name":"Yangli-ao Geng","orcid":"https://orcid.org/0000-0002-0084-5164"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangliao Geng","raw_affiliation_strings":["Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075882217"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16799772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4292","last_page":"4301"},"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":0.9993000030517578,"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":0.9993000030517578,"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/T12676","display_name":"Machine Learning and ELM","score":0.9779000282287598,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9355999827384949,"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/fusion","display_name":"Fusion","score":0.5986685752868652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5931840538978577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5056295394897461},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4481819272041321},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06396561861038208}],"concepts":[{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5986685752868652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5931840538978577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5056295394897461},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4481819272041321},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06396561861038208},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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:10.1145/3664647.3681164","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W102110531","https://openalex.org/W2111051539","https://openalex.org/W2473930607","https://openalex.org/W2525579820","https://openalex.org/W2560647685","https://openalex.org/W2612690371","https://openalex.org/W2806984819","https://openalex.org/W2895699061","https://openalex.org/W2963072899","https://openalex.org/W2963588172","https://openalex.org/W2967821093","https://openalex.org/W2971234316","https://openalex.org/W2972313371","https://openalex.org/W2980994576","https://openalex.org/W3017160304","https://openalex.org/W3030364939","https://openalex.org/W3034957837","https://openalex.org/W3096831136","https://openalex.org/W3098061682","https://openalex.org/W3105913416","https://openalex.org/W3106217498","https://openalex.org/W3107810305","https://openalex.org/W3125116114","https://openalex.org/W3168068006","https://openalex.org/W3170909290","https://openalex.org/W3173747377","https://openalex.org/W3173986289","https://openalex.org/W3178686235","https://openalex.org/W3182820356","https://openalex.org/W3204313571","https://openalex.org/W3209994584","https://openalex.org/W3211831669","https://openalex.org/W3212150209","https://openalex.org/W3213234780","https://openalex.org/W4212774754","https://openalex.org/W4221161784","https://openalex.org/W4246999471","https://openalex.org/W4247924304","https://openalex.org/W4254181784","https://openalex.org/W4287814827","https://openalex.org/W4295789386","https://openalex.org/W4295883599","https://openalex.org/W4298417552","https://openalex.org/W4320234134","https://openalex.org/W4361285887","https://openalex.org/W4367663429","https://openalex.org/W4379474343","https://openalex.org/W4382318202","https://openalex.org/W4385621649","https://openalex.org/W4386075595","https://openalex.org/W4386076049","https://openalex.org/W4390872637","https://openalex.org/W4393159974","https://openalex.org/W4394625757","https://openalex.org/W6741087337","https://openalex.org/W6751907932","https://openalex.org/W6802312230","https://openalex.org/W6803451136","https://openalex.org/W6850132393"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,17],"posterior":[1,19,38,94,118,150],"estimation":[2],"of":[3],"parameters":[4,33],"based":[5,123],"on":[6,124,154],"Bayesian":[7,78],"theory":[8],"is":[9,20],"a":[10,43,76,140,146],"crucial":[11],"technique":[12],"in":[13,46],"Incremental":[14],"Learning":[15],"(IL).":[16],"estimated":[18],"typically":[21],"utilized":[22],"to":[23,39,57,107,144],"impose":[24,55],"loss":[25,51,101],"regularization,":[26,102],"which":[27,103],"aligns":[28],"the":[29,35,58,65,92,105,120,125],"current":[30],"training":[31],"model":[32,59,106],"with":[34,119],"previously":[36],"learned":[37],"mitigate":[40],"catastrophic":[41,167],"forgetting,":[42],"major":[44],"challenge":[45],"IL.":[47],"However,":[48],"this":[49,71,73,116],"additional":[50],"regularization":[52],"can":[53],"also":[54,170],"detriment":[56],"learning,":[60],"preventing":[61],"it":[62],"from":[63],"reaching":[64],"true":[66],"global":[67],"optimum.":[68],"To":[69],"overcome":[70],"limitation,":[72],"paper":[74],"introduces":[75],"novel":[77],"IL":[79],"framework,":[80],"Robust":[81],"Parameter":[82],"Posterior":[83],"Fusion":[84],"(RP2F).":[85],"Unlike":[86],"traditional":[87],"methods,":[88],"RP2F":[89,138,162],"directly":[90],"estimates":[91],"parameter":[93],"for":[95],"new":[96,109,117],"data":[97],"without":[98],"introducing":[99],"extra":[100],"allows":[104],"accommodate":[108],"knowledge":[110,133,173],"more":[111],"sufficiently.":[112],"It":[113],"then":[114],"fuses":[115],"existing":[121],"ones":[122],"Maximum":[126],"A":[127],"Posteriori":[128],"(MAP)":[129],"principle,":[130],"ensuring":[131],"effective":[132],"sharing":[134],"across":[135],"tasks.":[136],"Furthermore,":[137],"incorporates":[139],"common":[141],"parameter-robustness":[142],"priori":[143],"facilitate":[145],"seamless":[147],"integration":[148],"during":[149],"fusion.":[151],"Comprehensive":[152],"experiments":[153],"CIFAR-10,":[155],"CIFAR-100,":[156],"and":[157],"Tiny-ImageNet":[158],"datasets":[159],"show":[160],"that":[161],"not":[163],"only":[164],"effectively":[165],"mitigates":[166],"forgetting":[168],"but":[169],"achieves":[171],"backward":[172],"transfer.":[174]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}