Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285410117> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4285410117 abstract "Designing an efficient neural architecture search method is an open and challenging problem over the last few years. A typical and well-performed strategy is gradient-based methods (i.e., Differentiable Architecture Search (DARTS)), which mainly searches the target sparse child graph from a trainable dense super graph. However, during the searching phrase, training the dense super graph usually requires excessively computational resources. Besides, the training based on a dense graph is excessively inefficient, and the memory consumption is prohibitively high. To alleviate this shortcoming, recently Iterative Shrinkage Thresholding Algorithm (ISTA), a sparse coding recovery algorithm, has been applied to DARTS, which directly optimizes the compressed representation of the super graph, and saves the memory and time consumption. Indeed, there are several such kinds of sparse coding recovery algorithms, and ISTA is not the best one in terms of recovery efficiency and effectiveness. To investigate the impact of different sparse coding recovery algorithm on performance in DARTS and provide some insights. Firstly, we design several sparse DARTS based on different sparse coding recovery algorithms (i.e., LISTA, CoD, and Lars). Then a series of controlled experiments on selected algorithms are conducted. The accuracy, search time and other indicators of the model are collected and compared. Sufficient theoretical analysis and experimental exploration reveal that the different compression algorithms show different characteristics on the sparse DARTS. Specifically, Lars-NAS tends to choose the operation with fewer parameters, while Cod-NAS is the simplest of the four recovery algorithms, and its consuming time is very short, but the CoD-NAS model is unstable. Particularly, LISTA-NAS achieves the accurate results with stable recovery time. Thus, it can be seen that all compression algorithms are available to utilized according to different environments and requirements." @default.
- W4285410117 created "2022-07-14" @default.
- W4285410117 creator A5012429599 @default.
- W4285410117 creator A5018999020 @default.
- W4285410117 creator A5050966101 @default.
- W4285410117 creator A5073535763 @default.
- W4285410117 date "2022-03-18" @default.
- W4285410117 modified "2023-10-16" @default.
- W4285410117 title "Sparse DARTS with Various Recovery Algorithms" @default.
- W4285410117 cites W1988619277 @default.
- W4285410117 cites W2000769684 @default.
- W4285410117 cites W2063978378 @default.
- W4285410117 cites W2115706991 @default.
- W4285410117 cites W2135046866 @default.
- W4285410117 cites W2141607429 @default.
- W4285410117 cites W2964081807 @default.
- W4285410117 cites W2965658867 @default.
- W4285410117 cites W2966284335 @default.
- W4285410117 cites W2981748264 @default.
- W4285410117 cites W2998227662 @default.
- W4285410117 cites W3105702746 @default.
- W4285410117 doi "https://doi.org/10.1145/3532213.3532225" @default.
- W4285410117 hasPublicationYear "2022" @default.
- W4285410117 type Work @default.
- W4285410117 citedByCount "1" @default.
- W4285410117 countsByYear W42854101172023 @default.
- W4285410117 crossrefType "proceedings-article" @default.
- W4285410117 hasAuthorship W4285410117A5012429599 @default.
- W4285410117 hasAuthorship W4285410117A5018999020 @default.
- W4285410117 hasAuthorship W4285410117A5050966101 @default.
- W4285410117 hasAuthorship W4285410117A5073535763 @default.
- W4285410117 hasConcept C102192266 @default.
- W4285410117 hasConcept C105795698 @default.
- W4285410117 hasConcept C11413529 @default.
- W4285410117 hasConcept C124066611 @default.
- W4285410117 hasConcept C13251829 @default.
- W4285410117 hasConcept C132525143 @default.
- W4285410117 hasConcept C154945302 @default.
- W4285410117 hasConcept C179372163 @default.
- W4285410117 hasConcept C179518139 @default.
- W4285410117 hasConcept C203776342 @default.
- W4285410117 hasConcept C205711294 @default.
- W4285410117 hasConcept C33923547 @default.
- W4285410117 hasConcept C41008148 @default.
- W4285410117 hasConcept C77637269 @default.
- W4285410117 hasConcept C80444323 @default.
- W4285410117 hasConceptScore W4285410117C102192266 @default.
- W4285410117 hasConceptScore W4285410117C105795698 @default.
- W4285410117 hasConceptScore W4285410117C11413529 @default.
- W4285410117 hasConceptScore W4285410117C124066611 @default.
- W4285410117 hasConceptScore W4285410117C13251829 @default.
- W4285410117 hasConceptScore W4285410117C132525143 @default.
- W4285410117 hasConceptScore W4285410117C154945302 @default.
- W4285410117 hasConceptScore W4285410117C179372163 @default.
- W4285410117 hasConceptScore W4285410117C179518139 @default.
- W4285410117 hasConceptScore W4285410117C203776342 @default.
- W4285410117 hasConceptScore W4285410117C205711294 @default.
- W4285410117 hasConceptScore W4285410117C33923547 @default.
- W4285410117 hasConceptScore W4285410117C41008148 @default.
- W4285410117 hasConceptScore W4285410117C77637269 @default.
- W4285410117 hasConceptScore W4285410117C80444323 @default.
- W4285410117 hasLocation W42854101171 @default.
- W4285410117 hasOpenAccess W4285410117 @default.
- W4285410117 hasPrimaryLocation W42854101171 @default.
- W4285410117 hasRelatedWork W1619754044 @default.
- W4285410117 hasRelatedWork W2009226074 @default.
- W4285410117 hasRelatedWork W2071247001 @default.
- W4285410117 hasRelatedWork W2128116911 @default.
- W4285410117 hasRelatedWork W2140245639 @default.
- W4285410117 hasRelatedWork W2143997830 @default.
- W4285410117 hasRelatedWork W2726024794 @default.
- W4285410117 hasRelatedWork W2785806594 @default.
- W4285410117 hasRelatedWork W2884728377 @default.
- W4285410117 hasRelatedWork W4251633608 @default.
- W4285410117 isParatext "false" @default.
- W4285410117 isRetracted "false" @default.
- W4285410117 workType "article" @default.