FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035572636> ?p ?o ?g. }

• W3035572636 abstract "Personal mobile sensing is fast permeating our daily lives to enable activity monitoring, healthcare and rehabilitation. Combined with deep learning, these applications have achieved significant success in recent years. Different from conventional cloud-based paradigms, running deep learning on devices offers several advantages including data privacy preservation and low-latency response for both model inference and update. Since data collection is costly in reality, Google’s Federated Learning offers not only complete data privacy but also better model robustness based on multiple user data. However, personal mobile sensing applications are mostly user-specific and highly affected by environment. As a result, continuous local changes may seriously affect the performance of a global model generated by Federated Learning. In addition, deploying Federated Learning on a local server, e.g., edge server, may quickly reach the bottleneck due to resource constraint and serious failure by attacks. Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning for personal mobile sensing applications. To address resource limitation, we propose a ChainSGD-reduce approach which includes a novel chain-directed Synchronous Stochastic Gradient Descent algorithm to effectively reduce overhead among multiple devices. We also design an agent-based multi-goal reinforcement learning mechanism to balance resources in a fair and efficient manner. Our evaluations show that our model training on off-the-shelf mobile devices achieves 2x to 3.5x faster than single-device training, and 1.5x faster than the master-slave approach." @default.
• W3035572636 created "2020-06-19" @default.
• W3035572636 creator A5054698524 @default.
• W3035572636 creator A5070538645 @default.
• W3035572636 creator A5071773009 @default.
• W3035572636 date "2020-04-01" @default.
• W3035572636 modified "2023-10-16" @default.
• W3035572636 title "MDLdroid: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing" @default.
• W3035572636 cites W1559136758 @default.
• W3035572636 cites W1991539813 @default.
• W3035572636 cites W2026297770 @default.
• W3035572636 cites W2060393849 @default.
• W3035572636 cites W2071385528 @default.
• W3035572636 cites W2082629283 @default.
• W3035572636 cites W2112796928 @default.
• W3035572636 cites W2126511896 @default.
• W3035572636 cites W2135352986 @default.
• W3035572636 cites W2151194859 @default.
• W3035572636 cites W2167489871 @default.
• W3035572636 cites W2538008957 @default.
• W3035572636 cites W2745300114 @default.
• W3035572636 cites W2807596698 @default.
• W3035572636 cites W2808423829 @default.
• W3035572636 cites W2809251854 @default.
• W3035572636 cites W2884294766 @default.
• W3035572636 cites W2912213068 @default.
• W3035572636 cites W2923546219 @default.
• W3035572636 cites W2937803535 @default.
• W3035572636 cites W2962755172 @default.
• W3035572636 cites W2963318081 @default.
• W3035572636 cites W2963964896 @default.
• W3035572636 cites W2964082633 @default.
• W3035572636 cites W2982475424 @default.
• W3035572636 cites W2984911178 @default.
• W3035572636 doi "https://doi.org/10.1109/ipsn48710.2020.00-45" @default.
• W3035572636 hasPublicationYear "2020" @default.
• W3035572636 type Work @default.
• W3035572636 sameAs 3035572636 @default.
• W3035572636 citedByCount "16" @default.
• W3035572636 countsByYear W30355726362019 @default.
• W3035572636 countsByYear W30355726362020 @default.
• W3035572636 countsByYear W30355726362021 @default.
• W3035572636 countsByYear W30355726362022 @default.
• W3035572636 countsByYear W30355726362023 @default.
• W3035572636 crossrefType "proceedings-article" @default.
• W3035572636 hasAuthorship W3035572636A5054698524 @default.
• W3035572636 hasAuthorship W3035572636A5070538645 @default.
• W3035572636 hasAuthorship W3035572636A5071773009 @default.
• W3035572636 hasBestOaLocation W30355726362 @default.
• W3035572636 hasConcept C104317684 @default.
• W3035572636 hasConcept C107457646 @default.
• W3035572636 hasConcept C108583219 @default.
• W3035572636 hasConcept C111919701 @default.
• W3035572636 hasConcept C119857082 @default.
• W3035572636 hasConcept C120314980 @default.
• W3035572636 hasConcept C136764020 @default.
• W3035572636 hasConcept C144543869 @default.
• W3035572636 hasConcept C149635348 @default.
• W3035572636 hasConcept C154945302 @default.
• W3035572636 hasConcept C185592680 @default.
• W3035572636 hasConcept C186967261 @default.
• W3035572636 hasConcept C2776214188 @default.
• W3035572636 hasConcept C2779960059 @default.
• W3035572636 hasConcept C2780513914 @default.
• W3035572636 hasConcept C31258907 @default.
• W3035572636 hasConcept C41008148 @default.
• W3035572636 hasConcept C55493867 @default.
• W3035572636 hasConcept C63479239 @default.
• W3035572636 hasConceptScore W3035572636C104317684 @default.
• W3035572636 hasConceptScore W3035572636C107457646 @default.
• W3035572636 hasConceptScore W3035572636C108583219 @default.
• W3035572636 hasConceptScore W3035572636C111919701 @default.
• W3035572636 hasConceptScore W3035572636C119857082 @default.
• W3035572636 hasConceptScore W3035572636C120314980 @default.
• W3035572636 hasConceptScore W3035572636C136764020 @default.
• W3035572636 hasConceptScore W3035572636C144543869 @default.
• W3035572636 hasConceptScore W3035572636C149635348 @default.
• W3035572636 hasConceptScore W3035572636C154945302 @default.
• W3035572636 hasConceptScore W3035572636C185592680 @default.
• W3035572636 hasConceptScore W3035572636C186967261 @default.
• W3035572636 hasConceptScore W3035572636C2776214188 @default.
• W3035572636 hasConceptScore W3035572636C2779960059 @default.
• W3035572636 hasConceptScore W3035572636C2780513914 @default.
• W3035572636 hasConceptScore W3035572636C31258907 @default.
• W3035572636 hasConceptScore W3035572636C41008148 @default.
• W3035572636 hasConceptScore W3035572636C55493867 @default.
• W3035572636 hasConceptScore W3035572636C63479239 @default.
• W3035572636 hasLocation W30355726361 @default.
• W3035572636 hasLocation W30355726362 @default.
• W3035572636 hasOpenAccess W3035572636 @default.
• W3035572636 hasPrimaryLocation W30355726361 @default.
• W3035572636 hasRelatedWork W3014300295 @default.
• W3035572636 hasRelatedWork W3164822677 @default.
• W3035572636 hasRelatedWork W4223943233 @default.
• W3035572636 hasRelatedWork W4225161397 @default.
• W3035572636 hasRelatedWork W4250304930 @default.
• W3035572636 hasRelatedWork W4312200629 @default.
• W3035572636 hasRelatedWork W4360585206 @default.
• W3035572636 hasRelatedWork W4364306694 @default.
• W3035572636 hasRelatedWork W4380075502 @default.

• next