FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204833512> ?p ?o ?g. }

• W3204833512 endingPage "595" @default.
• W3204833512 startingPage "578" @default.
• W3204833512 abstract "To facilitate the emerging applications in 5G networks, mobile network operators will provide many network functions in terms of control and prediction. Recently, they have recognized the power of machine learning (ML) and started to explore its potential to facilitate those network functions. Nevertheless, the current ML models for network functions are often derived in an offline manner, which is inefficient due to the excessive overhead for transmitting a huge volume of dataset to remote ML training clouds and failing to provide the incremental learning capability for the continuous model updating. As an alternative solution, we propose <i>Cocktail</i>, an incremental learning framework within a reference 5G network architecture. To achieve cost efficiency while increasing trained model accuracy, an efficient online data scheduling policy is essential. To this end, we formulate an online data scheduling problem to optimize the framework cost while alleviating the data skew issue caused by the capacity heterogeneity of training workers from the long-term perspective. We exploit the stochastic gradient descent to devise an online asymptotically optimal algorithm, including two optimal policies based on novel graph constructions for skew-aware data collection and data training. Small-scale testbed and large-scale simulations validate the superior performance of our proposed framework." @default.
• W3204833512 created "2021-10-11" @default.
• W3204833512 creator A5005130995 @default.
• W3204833512 creator A5042785211 @default.
• W3204833512 creator A5045685496 @default.
• W3204833512 creator A5053568911 @default.
• W3204833512 creator A5061774892 @default.
• W3204833512 creator A5076121175 @default.
• W3204833512 date "2022-02-01" @default.
• W3204833512 modified "2023-10-16" @default.
• W3204833512 title "Cost-Efficient and Skew-Aware Data Scheduling for Incremental Learning in 5G Networks" @default.
• W3204833512 cites W2101178122 @default.
• W3204833512 cites W2137152139 @default.
• W3204833512 cites W2338318698 @default.
• W3204833512 cites W2343448572 @default.
• W3204833512 cites W2521757593 @default.
• W3204833512 cites W2592036647 @default.
• W3204833512 cites W2615459164 @default.
• W3204833512 cites W2616867685 @default.
• W3204833512 cites W2624989916 @default.
• W3204833512 cites W2805049950 @default.
• W3204833512 cites W2810482148 @default.
• W3204833512 cites W2895051796 @default.
• W3204833512 cites W2910790589 @default.
• W3204833512 cites W2920095265 @default.
• W3204833512 cites W2921163933 @default.
• W3204833512 cites W2950865323 @default.
• W3204833512 cites W2962788286 @default.
• W3204833512 cites W2962814013 @default.
• W3204833512 cites W2969519626 @default.
• W3204833512 cites W3006403513 @default.
• W3204833512 cites W3010109240 @default.
• W3204833512 cites W3012125688 @default.
• W3204833512 cites W3015613093 @default.
• W3204833512 cites W3015636663 @default.
• W3204833512 cites W3038426846 @default.
• W3204833512 cites W3047304572 @default.
• W3204833512 cites W3105122387 @default.
• W3204833512 doi "https://doi.org/10.1109/jsac.2021.3118430" @default.
• W3204833512 hasPublicationYear "2022" @default.
• W3204833512 type Work @default.
• W3204833512 sameAs 3204833512 @default.
• W3204833512 citedByCount "1" @default.
• W3204833512 countsByYear W32048335122022 @default.
• W3204833512 crossrefType "journal-article" @default.
• W3204833512 hasAuthorship W3204833512A5005130995 @default.
• W3204833512 hasAuthorship W3204833512A5042785211 @default.
• W3204833512 hasAuthorship W3204833512A5045685496 @default.
• W3204833512 hasAuthorship W3204833512A5053568911 @default.
• W3204833512 hasAuthorship W3204833512A5061774892 @default.
• W3204833512 hasAuthorship W3204833512A5076121175 @default.
• W3204833512 hasConcept C119857082 @default.
• W3204833512 hasConcept C120314980 @default.
• W3204833512 hasConcept C126255220 @default.
• W3204833512 hasConcept C154945302 @default.
• W3204833512 hasConcept C165696696 @default.
• W3204833512 hasConcept C193415008 @default.
• W3204833512 hasConcept C206688291 @default.
• W3204833512 hasConcept C206729178 @default.
• W3204833512 hasConcept C31258907 @default.
• W3204833512 hasConcept C31395832 @default.
• W3204833512 hasConcept C33923547 @default.
• W3204833512 hasConcept C38652104 @default.
• W3204833512 hasConcept C41008148 @default.
• W3204833512 hasConcept C43711488 @default.
• W3204833512 hasConcept C50644808 @default.
• W3204833512 hasConcept C76155785 @default.
• W3204833512 hasConceptScore W3204833512C119857082 @default.
• W3204833512 hasConceptScore W3204833512C120314980 @default.
• W3204833512 hasConceptScore W3204833512C126255220 @default.
• W3204833512 hasConceptScore W3204833512C154945302 @default.
• W3204833512 hasConceptScore W3204833512C165696696 @default.
• W3204833512 hasConceptScore W3204833512C193415008 @default.
• W3204833512 hasConceptScore W3204833512C206688291 @default.
• W3204833512 hasConceptScore W3204833512C206729178 @default.
• W3204833512 hasConceptScore W3204833512C31258907 @default.
• W3204833512 hasConceptScore W3204833512C31395832 @default.
• W3204833512 hasConceptScore W3204833512C33923547 @default.
• W3204833512 hasConceptScore W3204833512C38652104 @default.
• W3204833512 hasConceptScore W3204833512C41008148 @default.
• W3204833512 hasConceptScore W3204833512C43711488 @default.
• W3204833512 hasConceptScore W3204833512C50644808 @default.
• W3204833512 hasConceptScore W3204833512C76155785 @default.
• W3204833512 hasFunder F4320321001 @default.
• W3204833512 hasFunder F4320323993 @default.
• W3204833512 hasFunder F4320330170 @default.
• W3204833512 hasFunder F4320330485 @default.
• W3204833512 hasFunder F4320334009 @default.
• W3204833512 hasIssue "2" @default.
• W3204833512 hasLocation W32048335121 @default.
• W3204833512 hasOpenAccess W3204833512 @default.
• W3204833512 hasPrimaryLocation W32048335121 @default.
• W3204833512 hasRelatedWork W1602950570 @default.
• W3204833512 hasRelatedWork W1669499690 @default.
• W3204833512 hasRelatedWork W1882733036 @default.
• W3204833512 hasRelatedWork W1969740176 @default.
• W3204833512 hasRelatedWork W1994781067 @default.
• W3204833512 hasRelatedWork W2039968861 @default.

• next