Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285108785> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4285108785 endingPage "21420" @default.
- W4285108785 startingPage "21409" @default.
- W4285108785 abstract "Edge devices, including, in particular, mobile devices, have been emerging as an increasingly more important platform for deep neural network (DNN) inference. Typically, multiple lightweight DNN models generated using different architectures and/or compression schemes can fit into a device, thus selecting an optimal one is crucial in order to maximize the users’ Quality of Experience (QoE) for edge inference. The existing approaches to device-aware DNN optimization are usually time consuming and not scalable in view of extremely diverse edge devices. More importantly, they focus on optimizing standard performance metrics (e.g., accuracy and latency), which may not translate into improvement of the users’ actual subjective QoE. In this article, we propose a novel automated and user-centric DNN selection engine, called <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$mathsf {Aquaman}$ </tex-math></inline-formula> , which keeps users into a closed loop and leverages their QoE feedback to guide DNN selection decisions. The core of <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$mathsf {Aquaman}$ </tex-math></inline-formula> is a neural network-based QoE predictor, which is continuously updated online. Additionally, we use neural bandit learning to balance exploitation and exploration, with a provably efficient QoE performance. Finally, we evaluate <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$mathsf {Aquaman}$ </tex-math></inline-formula> on a 15-user experimental study as well as synthetic simulations, demonstrating the effectiveness of <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$mathsf {Aquaman}$ </tex-math></inline-formula> ." @default.
- W4285108785 created "2022-07-14" @default.
- W4285108785 creator A5000834239 @default.
- W4285108785 creator A5039823039 @default.
- W4285108785 creator A5044771462 @default.
- W4285108785 creator A5046304741 @default.
- W4285108785 date "2022-11-01" @default.
- W4285108785 modified "2023-10-16" @default.
- W4285108785 title "Improving QoE of Deep Neural Network Inference on Edge Devices: A Bandit Approach" @default.
- W4285108785 doi "https://doi.org/10.1109/jiot.2022.3182728" @default.
- W4285108785 hasPublicationYear "2022" @default.
- W4285108785 type Work @default.
- W4285108785 citedByCount "0" @default.
- W4285108785 crossrefType "journal-article" @default.
- W4285108785 hasAuthorship W4285108785A5000834239 @default.
- W4285108785 hasAuthorship W4285108785A5039823039 @default.
- W4285108785 hasAuthorship W4285108785A5044771462 @default.
- W4285108785 hasAuthorship W4285108785A5046304741 @default.
- W4285108785 hasConcept C119857082 @default.
- W4285108785 hasConcept C154945302 @default.
- W4285108785 hasConcept C162307627 @default.
- W4285108785 hasConcept C2776214188 @default.
- W4285108785 hasConcept C33923547 @default.
- W4285108785 hasConcept C41008148 @default.
- W4285108785 hasConcept C45357846 @default.
- W4285108785 hasConcept C48044578 @default.
- W4285108785 hasConcept C50644808 @default.
- W4285108785 hasConcept C77088390 @default.
- W4285108785 hasConcept C80444323 @default.
- W4285108785 hasConcept C94375191 @default.
- W4285108785 hasConceptScore W4285108785C119857082 @default.
- W4285108785 hasConceptScore W4285108785C154945302 @default.
- W4285108785 hasConceptScore W4285108785C162307627 @default.
- W4285108785 hasConceptScore W4285108785C2776214188 @default.
- W4285108785 hasConceptScore W4285108785C33923547 @default.
- W4285108785 hasConceptScore W4285108785C41008148 @default.
- W4285108785 hasConceptScore W4285108785C45357846 @default.
- W4285108785 hasConceptScore W4285108785C48044578 @default.
- W4285108785 hasConceptScore W4285108785C50644808 @default.
- W4285108785 hasConceptScore W4285108785C77088390 @default.
- W4285108785 hasConceptScore W4285108785C80444323 @default.
- W4285108785 hasConceptScore W4285108785C94375191 @default.
- W4285108785 hasFunder F4320306076 @default.
- W4285108785 hasIssue "21" @default.
- W4285108785 hasLocation W42851087851 @default.
- W4285108785 hasOpenAccess W4285108785 @default.
- W4285108785 hasPrimaryLocation W42851087851 @default.
- W4285108785 hasRelatedWork W1525643724 @default.
- W4285108785 hasRelatedWork W2302028273 @default.
- W4285108785 hasRelatedWork W2364921833 @default.
- W4285108785 hasRelatedWork W2388030554 @default.
- W4285108785 hasRelatedWork W2461970972 @default.
- W4285108785 hasRelatedWork W2963058055 @default.
- W4285108785 hasRelatedWork W3136652852 @default.
- W4285108785 hasRelatedWork W4225616444 @default.
- W4285108785 hasRelatedWork W4380989335 @default.
- W4285108785 hasRelatedWork W1629725936 @default.
- W4285108785 hasVolume "9" @default.
- W4285108785 isParatext "false" @default.
- W4285108785 isRetracted "false" @default.
- W4285108785 workType "article" @default.