FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3188102017> ?p ?o ?g. }

• W3188102017 endingPage "822" @default.
• W3188102017 startingPage "808" @default.
• W3188102017 abstract "Over-the-air computation (AirComp) based federated learning (FL) is capable of achieving fast model aggregation by exploiting the waveform superposition property of multiple access channels. However, the model aggregation performance is severely limited by the unfavorable wireless propagation channels. In this paper, we propose to leverage intelligent reflecting surface (IRS) to achieve fast yet reliable model aggregation for AirComp-based FL. To optimize the learning performance, we formulate an optimization problem that jointly optimizes the device selection, the aggregation beamformer at the base station (BS), and the phase shifts at the IRS to maximize the number of devices participating in the model aggregation of each communication round under certain mean-squared-error (MSE) requirements. To tackle the formulated highly-intractable problem, we propose a two-step optimization framework. Specifically, we induce the sparsity of device selection in the first step, followed by solving a series of MSE minimization problems to find the maximum feasible device set in the second step. We then propose an alternating optimization framework, supported by the difference-of-convex-functions programming algorithm for low-rank optimization, to efficiently design the aggregation beamformers at the BS and phase shifts at the IRS. Simulation results will demonstrate that our proposed algorithm and the deployment of an IRS can achieve a lower training loss and higher FL prediction accuracy than the baseline algorithms." @default.
• W3188102017 created "2021-08-16" @default.
• W3188102017 creator A5008846227 @default.
• W3188102017 creator A5021296194 @default.
• W3188102017 creator A5022499594 @default.
• W3188102017 creator A5034563456 @default.
• W3188102017 creator A5041989556 @default.
• W3188102017 creator A5050651140 @default.
• W3188102017 creator A5079052203 @default.
• W3188102017 date "2022-02-01" @default.
• W3188102017 modified "2023-10-18" @default.
• W3188102017 title "Federated Learning via Intelligent Reflecting Surface" @default.
• W3188102017 cites W1561759234 @default.
• W3188102017 cites W1978666418 @default.
• W3188102017 cites W1996215314 @default.
• W3188102017 cites W2112796928 @default.
• W3188102017 cites W2140227342 @default.
• W3188102017 cites W2212194410 @default.
• W3188102017 cites W2803956200 @default.
• W3188102017 cites W2861117319 @default.
• W3188102017 cites W2907379776 @default.
• W3188102017 cites W2909289631 @default.
• W3188102017 cites W2912213068 @default.
• W3188102017 cites W2949670636 @default.
• W3188102017 cites W2950077417 @default.
• W3188102017 cites W2962804345 @default.
• W3188102017 cites W2963433607 @default.
• W3188102017 cites W2969343398 @default.
• W3188102017 cites W2969424089 @default.
• W3188102017 cites W2969519626 @default.
• W3188102017 cites W2975156709 @default.
• W3188102017 cites W2981138228 @default.
• W3188102017 cites W2990747873 @default.
• W3188102017 cites W2995554704 @default.
• W3188102017 cites W2999074226 @default.
• W3188102017 cites W3003592037 @default.
• W3188102017 cites W3006919779 @default.
• W3188102017 cites W3009554119 @default.
• W3188102017 cites W3011747750 @default.
• W3188102017 cites W3013719647 @default.
• W3188102017 cites W3039402952 @default.
• W3188102017 cites W3041971333 @default.
• W3188102017 cites W3047532379 @default.
• W3188102017 cites W3048433592 @default.
• W3188102017 cites W3059999910 @default.
• W3188102017 cites W3088898206 @default.
• W3188102017 cites W3089655738 @default.
• W3188102017 cites W3090615085 @default.
• W3188102017 cites W3103026331 @default.
• W3188102017 cites W3103657382 @default.
• W3188102017 cites W3111192549 @default.
• W3188102017 cites W3120117232 @default.
• W3188102017 cites W3129486236 @default.
• W3188102017 cites W3129922062 @default.
• W3188102017 cites W3138364951 @default.
• W3188102017 cites W3162819349 @default.
• W3188102017 cites W3212038668 @default.
• W3188102017 cites W4250589301 @default.
• W3188102017 doi "https://doi.org/10.1109/twc.2021.3099505" @default.
• W3188102017 hasPublicationYear "2022" @default.
• W3188102017 type Work @default.
• W3188102017 sameAs 3188102017 @default.
• W3188102017 citedByCount "48" @default.
• W3188102017 countsByYear W31881020172020 @default.
• W3188102017 countsByYear W31881020172021 @default.
• W3188102017 countsByYear W31881020172022 @default.
• W3188102017 countsByYear W31881020172023 @default.
• W3188102017 crossrefType "journal-article" @default.
• W3188102017 hasAuthorship W3188102017A5008846227 @default.
• W3188102017 hasAuthorship W3188102017A5021296194 @default.
• W3188102017 hasAuthorship W3188102017A5022499594 @default.
• W3188102017 hasAuthorship W3188102017A5034563456 @default.
• W3188102017 hasAuthorship W3188102017A5041989556 @default.
• W3188102017 hasAuthorship W3188102017A5050651140 @default.
• W3188102017 hasAuthorship W3188102017A5079052203 @default.
• W3188102017 hasBestOaLocation W31881020172 @default.
• W3188102017 hasConcept C105795698 @default.
• W3188102017 hasConcept C11413529 @default.
• W3188102017 hasConcept C126255220 @default.
• W3188102017 hasConcept C134306372 @default.
• W3188102017 hasConcept C137836250 @default.
• W3188102017 hasConcept C139945424 @default.
• W3188102017 hasConcept C153083717 @default.
• W3188102017 hasConcept C154945302 @default.
• W3188102017 hasConcept C27753989 @default.
• W3188102017 hasConcept C33923547 @default.
• W3188102017 hasConcept C41008148 @default.
• W3188102017 hasConcept C555944384 @default.
• W3188102017 hasConcept C68649174 @default.
• W3188102017 hasConcept C76155785 @default.
• W3188102017 hasConceptScore W3188102017C105795698 @default.
• W3188102017 hasConceptScore W3188102017C11413529 @default.
• W3188102017 hasConceptScore W3188102017C126255220 @default.
• W3188102017 hasConceptScore W3188102017C134306372 @default.
• W3188102017 hasConceptScore W3188102017C137836250 @default.
• W3188102017 hasConceptScore W3188102017C139945424 @default.
• W3188102017 hasConceptScore W3188102017C153083717 @default.
• W3188102017 hasConceptScore W3188102017C154945302 @default.

• next