Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100229743> ?p ?o ?g. }
- W3100229743 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.
- W3100229743 created "2020-11-23" @default.
- W3100229743 creator A5008846227 @default.
- W3100229743 creator A5010270772 @default.
- W3100229743 creator A5017541508 @default.
- W3100229743 creator A5022499594 @default.
- W3100229743 creator A5034563456 @default.
- W3100229743 creator A5041989556 @default.
- W3100229743 creator A5054836687 @default.
- W3100229743 date "2020-11-10" @default.
- W3100229743 modified "2023-09-27" @default.
- W3100229743 title "Federated Learning via Intelligent Reflecting Surface" @default.
- W3100229743 cites W1996215314 @default.
- W3100229743 cites W2140227342 @default.
- W3100229743 cites W2163605009 @default.
- W3100229743 cites W2212194410 @default.
- W3100229743 cites W2296319761 @default.
- W3100229743 cites W2340859457 @default.
- W3100229743 cites W2541884796 @default.
- W3100229743 cites W2604799547 @default.
- W3100229743 cites W2624989916 @default.
- W3100229743 cites W2803956200 @default.
- W3100229743 cites W2861117319 @default.
- W3100229743 cites W2902907165 @default.
- W3100229743 cites W2907379776 @default.
- W3100229743 cites W2912213068 @default.
- W3100229743 cites W2937693915 @default.
- W3100229743 cites W2949670636 @default.
- W3100229743 cites W2950077417 @default.
- W3100229743 cites W2962804345 @default.
- W3100229743 cites W2969343398 @default.
- W3100229743 cites W2969424089 @default.
- W3100229743 cites W2969519626 @default.
- W3100229743 cites W2975156709 @default.
- W3100229743 cites W2981138228 @default.
- W3100229743 cites W2990747873 @default.
- W3100229743 cites W2995554704 @default.
- W3100229743 cites W3009554119 @default.
- W3100229743 cites W3038145895 @default.
- W3100229743 cites W3039402952 @default.
- W3100229743 cites W3047532379 @default.
- W3100229743 cites W3048433592 @default.
- W3100229743 cites W3059999910 @default.
- W3100229743 cites W3083094609 @default.
- W3100229743 cites W3088898206 @default.
- W3100229743 cites W3090615085 @default.
- W3100229743 cites W3094089286 @default.
- W3100229743 cites W3111192549 @default.
- W3100229743 hasPublicationYear "2020" @default.
- W3100229743 type Work @default.
- W3100229743 sameAs 3100229743 @default.
- W3100229743 citedByCount "1" @default.
- W3100229743 countsByYear W31002297432021 @default.
- W3100229743 crossrefType "posted-content" @default.
- W3100229743 hasAuthorship W3100229743A5008846227 @default.
- W3100229743 hasAuthorship W3100229743A5010270772 @default.
- W3100229743 hasAuthorship W3100229743A5017541508 @default.
- W3100229743 hasAuthorship W3100229743A5022499594 @default.
- W3100229743 hasAuthorship W3100229743A5034563456 @default.
- W3100229743 hasAuthorship W3100229743A5041989556 @default.
- W3100229743 hasAuthorship W3100229743A5054836687 @default.
- W3100229743 hasConcept C105795698 @default.
- W3100229743 hasConcept C11413529 @default.
- W3100229743 hasConcept C126255220 @default.
- W3100229743 hasConcept C134306372 @default.
- W3100229743 hasConcept C137836250 @default.
- W3100229743 hasConcept C139945424 @default.
- W3100229743 hasConcept C147764199 @default.
- W3100229743 hasConcept C153083717 @default.
- W3100229743 hasConcept C154945302 @default.
- W3100229743 hasConcept C199360897 @default.
- W3100229743 hasConcept C27753989 @default.
- W3100229743 hasConcept C31258907 @default.
- W3100229743 hasConcept C33923547 @default.
- W3100229743 hasConcept C41008148 @default.
- W3100229743 hasConcept C68649174 @default.
- W3100229743 hasConceptScore W3100229743C105795698 @default.
- W3100229743 hasConceptScore W3100229743C11413529 @default.
- W3100229743 hasConceptScore W3100229743C126255220 @default.
- W3100229743 hasConceptScore W3100229743C134306372 @default.
- W3100229743 hasConceptScore W3100229743C137836250 @default.
- W3100229743 hasConceptScore W3100229743C139945424 @default.
- W3100229743 hasConceptScore W3100229743C147764199 @default.
- W3100229743 hasConceptScore W3100229743C153083717 @default.
- W3100229743 hasConceptScore W3100229743C154945302 @default.
- W3100229743 hasConceptScore W3100229743C199360897 @default.
- W3100229743 hasConceptScore W3100229743C27753989 @default.
- W3100229743 hasConceptScore W3100229743C31258907 @default.
- W3100229743 hasConceptScore W3100229743C33923547 @default.
- W3100229743 hasConceptScore W3100229743C41008148 @default.
- W3100229743 hasConceptScore W3100229743C68649174 @default.
- W3100229743 hasLocation W31002297431 @default.
- W3100229743 hasOpenAccess W3100229743 @default.
- W3100229743 hasPrimaryLocation W31002297431 @default.
- W3100229743 hasRelatedWork W2740479159 @default.
- W3100229743 hasRelatedWork W2751487380 @default.
- W3100229743 hasRelatedWork W2950145655 @default.
- W3100229743 hasRelatedWork W2960514293 @default.
- W3100229743 hasRelatedWork W2961311786 @default.
- W3100229743 hasRelatedWork W2975208030 @default.