{"id":"https://openalex.org/W4402353887","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649925","title":"Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning","display_name":"Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353887","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649925"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10649925","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10649925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5101430956","display_name":"Hikmat Khan","orcid":"https://orcid.org/0009-0008-2550-1991"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hikmat Khan","raw_affiliation_strings":["Rowan University,Glassboro,New Jersey,USA"],"affiliations":[{"raw_affiliation_string":"Rowan University,Glassboro,New Jersey,USA","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045996251","display_name":"Ghulam Rasool","orcid":"https://orcid.org/0000-0001-8551-0090"},"institutions":[{"id":"https://openalex.org/I3019308854","display_name":"Moffitt Cancer Center","ror":"https://ror.org/01xf75524","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I3019308854"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghulam Rasool","raw_affiliation_strings":["Moffitt Cancer Center,Tampa,Florida,USA"],"affiliations":[{"raw_affiliation_string":"Moffitt Cancer Center,Tampa,Florida,USA","institution_ids":["https://openalex.org/I3019308854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041401460","display_name":"Nidhal Bouaynaya","orcid":"https://orcid.org/0000-0002-8833-8414"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nidhal Carla Bouaynaya","raw_affiliation_strings":["Rowan University,Glassboro,New Jersey,USA"],"affiliations":[{"raw_affiliation_string":"Rowan University,Glassboro,New Jersey,USA","institution_ids":["https://openalex.org/I44265643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101430956"],"corresponding_institution_ids":["https://openalex.org/I44265643"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12986497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8932336568832397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.709487795829773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46789872646331787},{"id":"https://openalex.org/keywords/memory-problems","display_name":"Memory problems","score":0.4181561768054962},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3721822500228882},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.35146453976631165},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3441879153251648},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19157376885414124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14617183804512024}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8932336568832397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.709487795829773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46789872646331787},{"id":"https://openalex.org/C2908950501","wikidata":"https://www.wikidata.org/wiki/Q11072","display_name":"Memory problems","level":4,"score":0.4181561768054962},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3721822500228882},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.35146453976631165},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3441879153251648},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19157376885414124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14617183804512024},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.0},{"id":"https://openalex.org/C2779483572","wikidata":"https://www.wikidata.org/wiki/Q83030","display_name":"Dementia","level":3,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10649925","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10649925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1682403713","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2899771611","https://openalex.org/W2902456977","https://openalex.org/W2939137134","https://openalex.org/W2947461406","https://openalex.org/W2954929116","https://openalex.org/W2964189064","https://openalex.org/W3030364939","https://openalex.org/W3034856281","https://openalex.org/W3107810305","https://openalex.org/W3118608800","https://openalex.org/W3163939464","https://openalex.org/W3168149265","https://openalex.org/W3180392831","https://openalex.org/W3211384591","https://openalex.org/W4225484930","https://openalex.org/W4281773771","https://openalex.org/W4285579917","https://openalex.org/W4288337581","https://openalex.org/W4288359148","https://openalex.org/W4288363925","https://openalex.org/W4295883599","https://openalex.org/W4307464646","https://openalex.org/W4308236548","https://openalex.org/W4312269593","https://openalex.org/W4313028293","https://openalex.org/W4313137235","https://openalex.org/W4319299931","https://openalex.org/W4321230297","https://openalex.org/W4385571956","https://openalex.org/W4386211615","https://openalex.org/W4390872637","https://openalex.org/W4392114334","https://openalex.org/W4392173735","https://openalex.org/W4402092710","https://openalex.org/W6631943919","https://openalex.org/W6741087337","https://openalex.org/W6756040250","https://openalex.org/W6756754374","https://openalex.org/W6757555829","https://openalex.org/W6761100157","https://openalex.org/W6761283764","https://openalex.org/W6761472960","https://openalex.org/W6761839128","https://openalex.org/W6763462227","https://openalex.org/W6768928678","https://openalex.org/W6771809012","https://openalex.org/W6780397927","https://openalex.org/W6787972765","https://openalex.org/W6803011658","https://openalex.org/W6838571599","https://openalex.org/W6839834301","https://openalex.org/W6840245342","https://openalex.org/W6849414221","https://openalex.org/W6850441048"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W2989932438","https://openalex.org/W4387297750","https://openalex.org/W2186333919"],"abstract_inverted_index":{"Continual":[0],"learning":[1,5],"(CL)":[2],"focuses":[3],"on":[4,39,137],"non-stationary":[6],"data":[7],"distribution":[8,262],"without":[9],"forgetting":[10,65,246],"previous":[11],"knowledge.":[12],"Rehearsal-based":[13],"approaches":[14,24,149],"are":[15,180],"commonly":[16],"used":[17],"to":[18,47,87,109,127,153,161,193],"combat":[19],"catastrophic":[20,245],"forgetting.":[21],"However,":[22],"these":[23],"suffer":[25],"from":[26],"a":[27,51,83,124,250],"problem":[28],"called":[29],"\u201crehearsal":[30],"memory":[31,41,58,71,89,113,120,132,189,201,209,241],"overfitting\u201d,":[32],"where":[33],"the":[34,53,56,66,70,76,103,138,197,200,214,264,267],"model":[35,164],"becomes":[36],"too":[37],"specialized":[38],"limited":[40],"samples":[42],"and":[43,92,97,122,141,150,168,174,195,211,231,247,263],"loses":[44],"its":[45],"ability":[46,160],"generalize":[48],"effectively.":[49],"As":[50],"result,":[52],"effectiveness":[54],"of":[55,199,216,229,260,266,274],"rehearsal":[57,188],"progressively":[59],"decays,":[60],"ultimately":[61],"resulting":[62,248],"in":[63,131,187,239,249,277],"catastrophically":[64],"learned":[67],"tasks.To":[68],"address":[69],"overfitting":[72,186,210],"challenge,":[73],"we":[74,157,204],"introduce":[75,110],"Adversarially":[77],"Diversified":[78],"Rehearsal":[79],"Memory,":[80],"or":[81],"ADRM,":[82],"novel":[84],"method":[85],"designed":[86],"enrich":[88,271],"sample":[90],"diversity":[91,121],"bolster":[93],"resistance":[94],"against":[95],"natural":[96,167],"adversarial":[98,169],"noise":[99],"disruptions.":[100],"ADRM":[101,144,184,207,235],"employs":[102],"Fast":[104],"Gradient":[105],"Sign":[106],"Method":[107],"(FGSM)":[108],"adversarially":[111,175],"modified":[112],"samples,":[114,242],"achieving":[115],"two":[116],"primary":[117],"objectives:":[118],"enhancing":[119],"fostering":[123],"robust":[125],"response":[126],"continual":[128],"feature":[129,237,261,268,275],"drifts":[130,238],"samples.We":[133],"conducted":[134],"extensive":[135],"experiments":[136],"CIFAR10":[139,177],"dataset":[140],"found":[142],"that":[143,206,234],"outperforms":[145],"several":[146],"existing":[147,278],"CL":[148,163,217,240,253,279],"performs":[151],"comparable":[152],"state-of-the-art":[154],"methods.":[155],"Additionally,":[156,255],"demonstrated":[158],"ADRM\u2019s":[159],"enhance":[162],"robustness":[165,215],"under":[166],"conditions":[170],"by":[171,190],"using":[172],"CIFAR10-C":[173],"perturbed":[176],"datasets.Our":[178],"contributions":[179],"as":[181],"follows:":[182],"Firstly,":[183],"addresses":[185],"employing":[191],"FGSM":[192],"diversify":[194],"increase":[196],"complexity":[198],"buffer.":[202],"Secondly,":[203],"demonstrate":[205],"mitigates":[208,236],"significantly":[212,243],"improves":[213],"models,":[218],"which":[219],"is":[220,283],"crucial":[221],"for":[222],"safety-critical":[223],"applications.":[224],"Finally,":[225],"our":[226,256,272],"detailed":[227],"analysis":[228],"features":[230],"visualization":[232],"demonstrates":[233],"reducing":[244],"more":[251],"resilient":[252],"model.":[254],"in-depth":[257],"t-SNE":[258],"visualizations":[259],"quantification":[265],"similarity":[269],"further":[270],"understanding":[273],"representation":[276],"approaches.":[280],"Our":[281],"code":[282],"publically":[284],"available":[285],"at":[286],"https://github.com/hikmatkhan/ADRM.":[287]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}