{"id":"https://openalex.org/W4385484781","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191696","title":"Connection-Based Knowledge Transfer for Class Incremental Learning","display_name":"Connection-Based Knowledge Transfer for Class Incremental Learning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385484781","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191696"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108661506","display_name":"Guangzhi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhi Zhao","raw_affiliation_strings":["School of Mathematical Sciences, Peking University,Beijing,China","School of Mathematical Sciences, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041600410","display_name":"Kedian Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kedian Mu","raw_affiliation_strings":["School of Mathematical Sciences, Peking University,Beijing,China","School of Mathematical Sciences, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Mathematical Sciences, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9843000173568726,"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/T12676","display_name":"Machine Learning and ELM","score":0.9386000037193298,"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/forgetting","display_name":"Forgetting","score":0.921355128288269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7957785129547119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6691074967384338},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5950852036476135},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5873549580574036},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5736882090568542},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5486210584640503},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5233342051506042},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.4799390435218811},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4224380850791931},{"id":"https://openalex.org/keywords/isolation","display_name":"Isolation (microbiology)","score":0.4172842502593994},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4109938144683838},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32633182406425476}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.921355128288269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957785129547119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6691074967384338},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5950852036476135},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5873549580574036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5736882090568542},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5486210584640503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5233342051506042},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.4799390435218811},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4224380850791931},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.4172842502593994},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4109938144683838},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32633182406425476},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G8150328347","display_name":null,"funder_award_id":"61572002,61690201,61732001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1682403713","https://openalex.org/W2112796928","https://openalex.org/W2473930607","https://openalex.org/W2474280151","https://openalex.org/W2531327146","https://openalex.org/W2560647685","https://openalex.org/W2583761661","https://openalex.org/W2771964490","https://openalex.org/W2891707612","https://openalex.org/W2895699061","https://openalex.org/W2906141031","https://openalex.org/W2912351382","https://openalex.org/W2924984511","https://openalex.org/W2939137134","https://openalex.org/W2948734064","https://openalex.org/W2962690101","https://openalex.org/W2963049059","https://openalex.org/W2963061824","https://openalex.org/W2964137095","https://openalex.org/W2964189064","https://openalex.org/W2967821093","https://openalex.org/W3013325675","https://openalex.org/W3015680536","https://openalex.org/W3030364939","https://openalex.org/W3034292309","https://openalex.org/W3103225859","https://openalex.org/W3113238341","https://openalex.org/W3118608800","https://openalex.org/W3173493671","https://openalex.org/W3173986289","https://openalex.org/W3174101157","https://openalex.org/W3182158470","https://openalex.org/W4221148302","https://openalex.org/W4301163820","https://openalex.org/W4319988532","https://openalex.org/W6713132643","https://openalex.org/W6720926796","https://openalex.org/W6728622933","https://openalex.org/W6732467815","https://openalex.org/W6741217325","https://openalex.org/W6746643698","https://openalex.org/W6755109808","https://openalex.org/W6757988401","https://openalex.org/W6758388730","https://openalex.org/W6760784890","https://openalex.org/W6763000130","https://openalex.org/W6776451990","https://openalex.org/W6785725522","https://openalex.org/W6810212661","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W4287067590","https://openalex.org/W3186262193","https://openalex.org/W3192176272","https://openalex.org/W4297634446","https://openalex.org/W4391158518","https://openalex.org/W4381322349","https://openalex.org/W3085307110","https://openalex.org/W3157400488","https://openalex.org/W4382021137","https://openalex.org/W2892655153"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,25,57,94,161,189],"problem":[3],"of":[4,24,28,70,108,128,191],"class":[5],"incremental":[6,29,185],"learning":[7,186],"(CIL),":[8],"where":[9],"an":[10],"agent":[11],"aims":[12],"to":[13,41,116,137,159],"learn":[14,138],"new":[15,62,82,147],"classes":[16,63,72],"continually":[17],"without":[18],"forgetting":[19,35,167],"previous":[20,149],"ones.":[21],"As":[22,54],"one":[23],"mainstream":[26],"paradigms":[27],"learning,":[30],"parameter":[31],"isolation":[32],"methods":[33],"prevent":[34],"by":[36,92,155,168],"allocating":[37],"different":[38,139],"model":[39],"parameters":[40,172],"each":[42,118],"task,":[43],"but":[44],"knowledge":[45,122,176],"transfer":[46,123],"across":[47],"tasks":[48,97,111],"is":[49,64,73,135],"difficult":[50],"and":[51,61,98,112,124,173],"usually":[52],"overlooked.":[53],"a":[55,81,106,131,156],"consequence,":[56],"discriminability":[58],"between":[59],"old":[60,71],"limited,":[65],"especially":[66],"when":[67],"training":[68],"data":[69],"not":[74],"accessible.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79,102],"propose":[80],"data-free":[83],"approach":[84],"named":[85],"Twin":[86],"Contrastive":[87],"Networks":[88],"(TCN)":[89],"for":[90,142],"CIL":[91,104],"utilizing":[93],"connections":[95],"among":[96],"network":[99,133],"parameters.":[100],"Specifically,":[101],"treat":[103],"as":[105],"sequence":[107],"one-class":[109],"classification":[110],"train":[113],"separate":[114],"classifiers":[115],"identify":[117],"class.":[119],"To":[120],"facilitate":[121],"make":[125],"full":[126],"use":[127],"accumulated":[129],"knowledge,":[130],"twin":[132,150],"structure":[134],"adopted":[136],"feature":[140],"representations":[141],"future":[143],"use.":[144],"While":[145],"encountering":[146],"classes,":[148],"networks":[151],"are":[152],"utilized":[153],"directly":[154],"contrastive":[157],"loss":[158],"improve":[160],"model's":[162],"discriminability.":[163],"TCN":[164],"avoids":[165],"catastrophic":[166],"fixing":[169],"all":[170],"learnt":[171],"leverages":[174],"prior":[175],"contained":[177],"in":[178],"networks.":[179],"Experiments":[180],"on":[181],"three":[182],"widely":[183],"used":[184],"benchmarks":[187],"verify":[188],"effectiveness":[190],"TCN.":[192]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}