Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996752431> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2996752431 abstract "Deep neural networks (DNNs) are the key techniques to enable edge/fog intelligence. By far, it remains challenging to conduct distributed deployment of DNN models onto resource-constrained fog nodes with low latency. Existing solutions adopt either model compression techniques to reduce the computation loads on fog nodes, or horizontal model partition techniques, which exploit particular communication and computation patterns to partition different layers of DNNs onto fog nodes. Nonetheless, sometimes even resource demands of particular layers can be unaffordable to fog nodes, which makes horizontal partition inadequate and calls for the joint design of vertical and horizontal model partition. Besides, model partition and compression may lead to degraded inference accuracy, but approaches to compensate such accuracy loss remain unexplored.In this paper, we propose an integrated efficient distributed deep learning (EDDL) framework to address the above challenges. Particularly, we adopt balanced incomplete block design (BIBD) methods to reduce computation loads on fog nodes by removing some data flows in DNNs in a systematic and structured manner. By leveraging grouped convolution techniques, we propose a practical scheme to conduct horizontal and vertical model partition jointly. Moreover, we integrate multi-task learning and ensemble learning techniques to further improve the inference accuracy. Simulation results verify the effectiveness of EDDL framework in achieving notable reduction in computation load and memory footprint with mild loss of inference accuracy." @default.
- W2996752431 created "2019-12-26" @default.
- W2996752431 creator A5002187549 @default.
- W2996752431 creator A5025859650 @default.
- W2996752431 creator A5049692788 @default.
- W2996752431 creator A5080717946 @default.
- W2996752431 date "2019-12-01" @default.
- W2996752431 modified "2023-09-27" @default.
- W2996752431 title "An Efficient Distributed Deep Learning Framework for Fog-Based IoT Systems" @default.
- W2996752431 cites W2011032342 @default.
- W2996752431 cites W2075157159 @default.
- W2996752431 cites W2194775991 @default.
- W2996752431 cites W2472333518 @default.
- W2996752431 cites W2531409750 @default.
- W2996752431 cites W2605258629 @default.
- W2996752431 cites W2618530766 @default.
- W2996752431 cites W2809251854 @default.
- W2996752431 cites W2912654452 @default.
- W2996752431 cites W2962677625 @default.
- W2996752431 cites W2962883027 @default.
- W2996752431 cites W2963477586 @default.
- W2996752431 cites W2964248614 @default.
- W2996752431 doi "https://doi.org/10.1109/globecom38437.2019.9014056" @default.
- W2996752431 hasPublicationYear "2019" @default.
- W2996752431 type Work @default.
- W2996752431 sameAs 2996752431 @default.
- W2996752431 citedByCount "8" @default.
- W2996752431 countsByYear W29967524312021 @default.
- W2996752431 countsByYear W29967524312022 @default.
- W2996752431 crossrefType "proceedings-article" @default.
- W2996752431 hasAuthorship W2996752431A5002187549 @default.
- W2996752431 hasAuthorship W2996752431A5025859650 @default.
- W2996752431 hasAuthorship W2996752431A5049692788 @default.
- W2996752431 hasAuthorship W2996752431A5080717946 @default.
- W2996752431 hasConcept C108583219 @default.
- W2996752431 hasConcept C120314980 @default.
- W2996752431 hasConcept C154945302 @default.
- W2996752431 hasConcept C2986652147 @default.
- W2996752431 hasConcept C38652104 @default.
- W2996752431 hasConcept C41008148 @default.
- W2996752431 hasConcept C81860439 @default.
- W2996752431 hasConceptScore W2996752431C108583219 @default.
- W2996752431 hasConceptScore W2996752431C120314980 @default.
- W2996752431 hasConceptScore W2996752431C154945302 @default.
- W2996752431 hasConceptScore W2996752431C2986652147 @default.
- W2996752431 hasConceptScore W2996752431C38652104 @default.
- W2996752431 hasConceptScore W2996752431C41008148 @default.
- W2996752431 hasConceptScore W2996752431C81860439 @default.
- W2996752431 hasLocation W29967524311 @default.
- W2996752431 hasOpenAccess W2996752431 @default.
- W2996752431 hasPrimaryLocation W29967524311 @default.
- W2996752431 hasRelatedWork W2618984630 @default.
- W2996752431 hasRelatedWork W2731899572 @default.
- W2996752431 hasRelatedWork W2900070427 @default.
- W2996752431 hasRelatedWork W2908407949 @default.
- W2996752431 hasRelatedWork W2939353110 @default.
- W2996752431 hasRelatedWork W2958794440 @default.
- W2996752431 hasRelatedWork W3009238340 @default.
- W2996752431 hasRelatedWork W3095247034 @default.
- W2996752431 hasRelatedWork W3215138031 @default.
- W2996752431 hasRelatedWork W4225852903 @default.
- W2996752431 isParatext "false" @default.
- W2996752431 isRetracted "false" @default.
- W2996752431 magId "2996752431" @default.
- W2996752431 workType "article" @default.