{"id":"https://openalex.org/W4386597146","doi":"https://doi.org/10.1109/icip49359.2023.10222032","title":"Locally Accumulated Adam For Distributed Training With Sparse Updates","display_name":"Locally Accumulated Adam For Distributed Training With Sparse Updates","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386597146","doi":"https://doi.org/10.1109/icip49359.2023.10222032"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222032","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5101694525","display_name":"Yiming Chen","orcid":"https://orcid.org/0000-0002-0845-6155"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yiming Chen","raw_affiliation_strings":["Vrije Universiteit Brussel (VUB),ETRO Department,Brussels,Belgium,B-1050","Imec, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel (VUB),ETRO Department,Brussels,Belgium,B-1050","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Imec, Leuven, Belgium","institution_ids":["https://openalex.org/I4210114974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043511500","display_name":"Nikos Deligiannis","orcid":"https://orcid.org/0000-0001-9300-5860"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nikos Deligiannis","raw_affiliation_strings":["Vrije Universiteit Brussel (VUB),ETRO Department,Brussels,Belgium,B-1050","Imec, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel (VUB),ETRO Department,Brussels,Belgium,B-1050","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Imec, Leuven, Belgium","institution_ids":["https://openalex.org/I4210114974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"31","issue":null,"first_page":"2395","last_page":"2399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9980000257492065,"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":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.8013486862182617},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6851775050163269},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5626048445701599},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5163856148719788},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48151907324790955},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4577658474445343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4476303160190582},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34654951095581055},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33033299446105957},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3033856451511383},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10369083285331726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8013486862182617},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6851775050163269},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5626048445701599},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5163856148719788},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48151907324790955},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4577658474445343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4476303160190582},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34654951095581055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33033299446105957},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3033856451511383},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10369083285331726},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icip49359.2023.10222032","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:171014","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/locally-accumulated-adam-for-distributed-training-with-sparse-updates(577d8ad1-6db9-46f8-8c6c-9a8389f049f6).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:187535","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2073135371","display_name":"Dictionary Learning and Distributed Inference for the Processing of Large-scale Heterogeneous Image Data (DOLPHIN)","funder_award_id":"G0A2617N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2117539524","https://openalex.org/W2127941149","https://openalex.org/W2171943915","https://openalex.org/W2194775991","https://openalex.org/W2407022425","https://openalex.org/W2606891064","https://openalex.org/W2630837129","https://openalex.org/W2766140019","https://openalex.org/W2769644379","https://openalex.org/W3101036738","https://openalex.org/W3118608800","https://openalex.org/W3138516171","https://openalex.org/W3166384310","https://openalex.org/W3203803206","https://openalex.org/W4255556797","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6679154944","https://openalex.org/W6739901393","https://openalex.org/W6745723224","https://openalex.org/W6746200960","https://openalex.org/W6746839373","https://openalex.org/W6763509872","https://openalex.org/W6778485988","https://openalex.org/W6784333009","https://openalex.org/W6787972765","https://openalex.org/W6790169199","https://openalex.org/W6802648153"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"The":[0],"high":[1],"bandwidth":[2],"required":[3],"for":[4,10,25],"gradient":[5,23,41],"exchange":[6],"is":[7,84],"a":[8,54],"bottleneck":[9],"the":[11,65,104],"distributed":[12,50,109],"training":[13,110],"of":[14],"large":[15],"transformer":[16],"models.":[17],"Most":[18],"sparsification":[19,83],"approaches":[20],"focus":[21],"on":[22],"compression":[24],"convolutional":[26],"neural":[27],"networks":[28],"(CNNs)":[29],"optimized":[30],"by":[31,63],"SGD.":[32],"In":[33],"this":[34,61],"work,":[35],"we":[36,59],"show":[37,81,97],"that":[38,82,98],"performing":[39],"local":[40],"accumulation":[42],"when":[43],"using":[44],"Adam":[45],"to":[46,53,86],"optimize":[47],"transformers":[48],"in":[49,108],"fashion":[51],"leads":[52],"misled":[55],"optimization":[56,66,106],"direction":[57,67,107],"and":[58,79,94],"address":[60],"problem":[62],"accumulating":[64],"locally.":[68],"We":[69],"also":[70],"empirically":[71],"demonstrate":[72],"most":[73],"sparse":[74,114],"gradients":[75],"do":[76],"not":[77],"overlap":[78],"thus":[80],"comparable":[85],"an":[87],"asynchronous":[88],"update.":[89],"Our":[90],"experiments":[91],"with":[92],"classification":[93],"segmentation":[95],"tasks":[96],"our":[99],"method":[100],"can":[101],"still":[102],"maintain":[103],"correct":[105],"event":[111],"under":[112],"highly":[113],"updates.":[115]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}