Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383749396> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4383749396 abstract "Many mobile applications are now integrating deep learning models into their core functionality. These functionalities have diverse latency requirements while demanding high-accuracy results. Currently, mobile applications statically decide to use either in-cloud inference, relying on a fast and consistent network, or on-device execution, relying on sufficient local resources. However, neither mobile networks nor computation resources deliver consistent performance in practice. Consequently, mobile inference often experiences variable performance or struggles to meet performance goals, when inference execution decisions are not made dynamically. In this paper, we introduce Layer Cake, a deep-learning inference framework that dynamically selects the best model and location for executing inferences. Layercake accomplishes this by tracking model state and availability, both locally and remotely, as well as the network bandwidth, allowing for accurate estimations of model response time. By doing so, Layercake achieves latency targets in up to 96.4% of cases, which is an improvement of 16.7% over similar systems, while decreasing the cost of cloud-based resources by over 68.33% than in-cloud inference." @default.
- W4383749396 created "2023-07-11" @default.
- W4383749396 creator A5041264523 @default.
- W4383749396 creator A5051346938 @default.
- W4383749396 date "2023-05-01" @default.
- W4383749396 modified "2023-09-27" @default.
- W4383749396 title "Layercake: Efficient Inference Serving with Cloud and Mobile Resources" @default.
- W4383749396 cites W2099517310 @default.
- W4383749396 cites W2102849319 @default.
- W4383749396 cites W2183341477 @default.
- W4383749396 cites W2321921970 @default.
- W4383749396 cites W2742405391 @default.
- W4383749396 cites W2747681982 @default.
- W4383749396 cites W2792447253 @default.
- W4383749396 cites W2949231165 @default.
- W4383749396 cites W2962883027 @default.
- W4383749396 cites W2963988417 @default.
- W4383749396 cites W2983708784 @default.
- W4383749396 cites W2998611528 @default.
- W4383749396 cites W3026174634 @default.
- W4383749396 cites W3088076788 @default.
- W4383749396 cites W3094307698 @default.
- W4383749396 cites W3095488153 @default.
- W4383749396 cites W3101962329 @default.
- W4383749396 cites W3107995663 @default.
- W4383749396 cites W3156449479 @default.
- W4383749396 cites W3156987284 @default.
- W4383749396 cites W3162157550 @default.
- W4383749396 cites W4205137559 @default.
- W4383749396 cites W4236099117 @default.
- W4383749396 doi "https://doi.org/10.1109/ccgrid57682.2023.00027" @default.
- W4383749396 hasPublicationYear "2023" @default.
- W4383749396 type Work @default.
- W4383749396 citedByCount "0" @default.
- W4383749396 crossrefType "proceedings-article" @default.
- W4383749396 hasAuthorship W4383749396A5041264523 @default.
- W4383749396 hasAuthorship W4383749396A5051346938 @default.
- W4383749396 hasConcept C108583219 @default.
- W4383749396 hasConcept C111919701 @default.
- W4383749396 hasConcept C11413529 @default.
- W4383749396 hasConcept C120314980 @default.
- W4383749396 hasConcept C144543869 @default.
- W4383749396 hasConcept C154945302 @default.
- W4383749396 hasConcept C186967261 @default.
- W4383749396 hasConcept C2776214188 @default.
- W4383749396 hasConcept C2779191767 @default.
- W4383749396 hasConcept C31258907 @default.
- W4383749396 hasConcept C41008148 @default.
- W4383749396 hasConcept C45374587 @default.
- W4383749396 hasConcept C76155785 @default.
- W4383749396 hasConcept C79403827 @default.
- W4383749396 hasConcept C79974875 @default.
- W4383749396 hasConcept C82876162 @default.
- W4383749396 hasConceptScore W4383749396C108583219 @default.
- W4383749396 hasConceptScore W4383749396C111919701 @default.
- W4383749396 hasConceptScore W4383749396C11413529 @default.
- W4383749396 hasConceptScore W4383749396C120314980 @default.
- W4383749396 hasConceptScore W4383749396C144543869 @default.
- W4383749396 hasConceptScore W4383749396C154945302 @default.
- W4383749396 hasConceptScore W4383749396C186967261 @default.
- W4383749396 hasConceptScore W4383749396C2776214188 @default.
- W4383749396 hasConceptScore W4383749396C2779191767 @default.
- W4383749396 hasConceptScore W4383749396C31258907 @default.
- W4383749396 hasConceptScore W4383749396C41008148 @default.
- W4383749396 hasConceptScore W4383749396C45374587 @default.
- W4383749396 hasConceptScore W4383749396C76155785 @default.
- W4383749396 hasConceptScore W4383749396C79403827 @default.
- W4383749396 hasConceptScore W4383749396C79974875 @default.
- W4383749396 hasConceptScore W4383749396C82876162 @default.
- W4383749396 hasFunder F4320306076 @default.
- W4383749396 hasLocation W43837493961 @default.
- W4383749396 hasOpenAccess W4383749396 @default.
- W4383749396 hasPrimaryLocation W43837493961 @default.
- W4383749396 hasRelatedWork W2019527080 @default.
- W4383749396 hasRelatedWork W2021754657 @default.
- W4383749396 hasRelatedWork W2161346040 @default.
- W4383749396 hasRelatedWork W2214728542 @default.
- W4383749396 hasRelatedWork W2969989898 @default.
- W4383749396 hasRelatedWork W3006515133 @default.
- W4383749396 hasRelatedWork W3026174634 @default.
- W4383749396 hasRelatedWork W3042877534 @default.
- W4383749396 hasRelatedWork W4281385823 @default.
- W4383749396 hasRelatedWork W4312728238 @default.
- W4383749396 isParatext "false" @default.
- W4383749396 isRetracted "false" @default.
- W4383749396 workType "article" @default.