1. Identificação | |
Tipo de Referência | Artigo em Evento (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Código do Detentor | ibi 8JMKD3MGPEW34M/46T9EHH |
Identificador | 8JMKD3MGPEW34M/43BCFTS |
Repositório | sid.inpe.br/sibgrapi/2020/09.29.21.31 |
Última Atualização | 2020:09.29.21.31.15 (UTC) administrator |
Repositório de Metadados | sid.inpe.br/sibgrapi/2020/09.29.21.31.15 |
Última Atualização dos Metadados | 2022:06.14.00.00.12 (UTC) administrator |
DOI | 10.1109/SIBGRAPI51738.2020.00044 |
Chave de Citação | MagalhãesSilGomMarSil:2020:EvEmWi |
Título | Evaluating the Emergence of Winning Tickets by Structured Pruning of Convolutional Networks |
Formato | On-line |
Ano | 2020 |
Data de Acesso | 17 maio 2024 |
Número de Arquivos | 1 |
Tamanho | 182 KiB |
|
2. Contextualização | |
Autor | 1 Magalhães, Whendell Feijó 2 Silva, Jeferson Ferreira da 3 Gomes, Herman Martins 4 Marinho, Leandro Balby 5 Silveira, Plínio |
Afiliação | 1 Federal University of Campina Grande 2 Federal University of Campina Grande 3 Federal University of Campina Grande 4 Federal University of Campina Grande 5 Hewlett Packard Enterprise, Brazil |
Editor | Musse, Soraia Raupp Cesar Junior, Roberto Marcondes Pelechano, Nuria Wang, Zhangyang (Atlas) |
Endereço de e-Mail | whendell@copin.ufcg.edu.br |
Nome do Evento | Conference on Graphics, Patterns and Images, 33 (SIBGRAPI) |
Localização do Evento | Porto de Galinhas (virtual) |
Data | 7-10 Nov. 2020 |
Editora (Publisher) | IEEE Computer Society |
Cidade da Editora | Los Alamitos |
Título do Livro | Proceedings |
Tipo Terciário | Full Paper |
Histórico (UTC) | 2020-09-29 21:31:15 :: whendell@copin.ufcg.edu.br -> administrator :: 2022-06-14 00:00:12 :: administrator -> whendell@copin.ufcg.edu.br :: 2020 |
|
3. Conteúdo e estrutura | |
É a matriz ou uma cópia? | é a matriz |
Estágio do Conteúdo | concluido |
Transferível | 1 |
Tipo de Versão | finaldraft |
Palavras-Chave | neural network compression structured pruning winning tickets weight rewinding learning rate rewinding |
Resumo | The recently introduced Lottery Ticket Hypothesis has created a new investigation front in neural network pruning. The hypothesis states that it is possible to find subnetworks with high generalization capabilities (winning tickets) from an over-parameterized neural network. One step of the algorithm implementing the hypothesis requires resetting the weights of the pruned network to their initial random values. More recent variations of this step may involve: (i) resetting the weights to the values they had at an early epoch of the unpruned network training, or (ii) keeping the final training weights and resetting only the learning rate schedule. Despite some studies have investigated the above variations, mostly with unstructured pruning, we do not know of existing evaluations focusing on structured pruning regarding local and global pruning variations. In this context, this paper presents novel empirical evidence that it is possible to obtain winning tickets when performing structured pruning of convolutional neural networks. We setup an experiment using the VGG-16 network trained on the CIFAR-10 dataset and compared networks (pruned at different compression levels) got by weight rewinding and learning rate rewinding methods, under local and global pruning regimes. We use the unpruned network as baseline and also compare the resulting pruned networks with their versions trained with randomly initialized weights. Overall, local pruning failed to find winning tickets for both rewinding methods. When using global pruning, weight rewinding produced a few winning tickets (limited to low pruning levels only) and performed nearly the same or worse compared to random initialization. Learning rate rewinding, under global pruning, produced the best results, since it has found winning tickets at most pruning levels and outperformed the baseline. |
Arranjo 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2020 > Evaluating the Emergence... |
Arranjo 2 | urlib.net > SDLA > Fonds > Full Index > Evaluating the Emergence... |
Conteúdo da Pasta doc | acessar |
Conteúdo da Pasta source | não têm arquivos |
Conteúdo da Pasta agreement | |
|
4. Condições de acesso e uso | |
URL dos dados | http://urlib.net/ibi/8JMKD3MGPEW34M/43BCFTS |
URL dos dados zipados | http://urlib.net/zip/8JMKD3MGPEW34M/43BCFTS |
Idioma | en |
Arquivo Alvo | 133.pdf |
Grupo de Usuários | whendell@copin.ufcg.edu.br |
Visibilidade | shown |
Permissão de Atualização | não transferida |
|
5. Fontes relacionadas | |
Repositório Espelho | sid.inpe.br/banon/2001/03.30.15.38.24 |
Unidades Imediatamente Superiores | 8JMKD3MGPEW34M/43G4L9S 8JMKD3MGPEW34M/4742MCS |
Lista de Itens Citando | sid.inpe.br/sibgrapi/2020/10.28.20.46 5 |
Acervo Hospedeiro | sid.inpe.br/banon/2001/03.30.15.38 |
|
6. Notas | |
Campos Vazios | archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume |
|
7. Controle da descrição | |
e-Mail (login) | whendell@copin.ufcg.edu.br |
atualizar | |
|