FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293195474> ?p ?o ?g. }

• W4293195474 endingPage "9365" @default.
• W4293195474 startingPage "9351" @default.
• W4293195474 abstract "Federated learning (FL) is a popular distributed learning paradigm, in which a global model at a server learns private data of clients without data shared among clients or the server. In this paper, we consider FL over a noisy fading multiple access channel (MAC) via over-the-air computation (AirComp). Benefiting from waveform-superposition propriety of wireless signals, AirComp is able to achieve fast aggregations in FL and improve spectral efficiency. However, most of the schemes exploiting AirComp require intensive channel estimations as the demands from precoders, which results in considerable communication overheads. For this reason, we propose two novel FL schemes with statistical channel state information (FL-SCSI-A and FL-SCSI-B) to reduce the efforts required by channel estimations. In FL-SCSI-A, precoders adjust phases of transmitted signals with phases of instant channel state information (CSI), and scale transmitted signal powers based on statistical CSI. The precoder design has the following two advantages. First, phases of instant CSI can be easier to estimate than complete instant CSI. Second, since clients only need to estimate phases of their own instant CSI (instead of CSI of all clients), with channel reciprocity, this can be easily achieved by letting the server broadcast pilots to all clients. The server in FL-SCSI-A is also efficient. It only needs to estimate the sum of channel gains of all clients, which can be easily achieved by letting clients transmit pilots simultaneously. To further reduce the communication overhead, FL-SCSI-B is proposed. The precoders in FL-SCSI-B are similar to FL-SCSI-A, while the server does not require any knowledge of instant CSI, which reduces the demands of channel estimations. For both schemes, we prove that the distortion caused by the noisy fading MAC is bounded, and the convergences of the learning processes are guaranteed for strongly smooth losses with heterogeneous data assumptions. Experimental results show that the proposed schemes perform better than benchmark schemes while reducing efforts required by channel estimation." @default.
• W4293195474 created "2022-08-27" @default.
• W4293195474 creator A5038619327 @default.
• W4293195474 creator A5063594676 @default.
• W4293195474 date "2022-11-01" @default.
• W4293195474 modified "2023-10-13" @default.
• W4293195474 title "Federated Learning via Over-the-Air Computation With Statistical Channel State Information" @default.
• W4293195474 cites W1561759234 @default.
• W4293195474 cites W2087039524 @default.
• W4293195474 cites W2140227342 @default.
• W4293195474 cites W2861117319 @default.
• W4293195474 cites W2954996726 @default.
• W4293195474 cites W2981138228 @default.
• W4293195474 cites W2989289980 @default.
• W4293195474 cites W2999074226 @default.
• W4293195474 cites W3006919779 @default.
• W4293195474 cites W3015613093 @default.
• W4293195474 cites W3015901293 @default.
• W4293195474 cites W3028318515 @default.
• W4293195474 cites W3045027907 @default.
• W4293195474 cites W3047206701 @default.
• W4293195474 cites W3086073975 @default.
• W4293195474 cites W3088234149 @default.
• W4293195474 cites W3090615085 @default.
• W4293195474 cites W3103802018 @default.
• W4293195474 doi "https://doi.org/10.1109/twc.2022.3175887" @default.
• W4293195474 hasPublicationYear "2022" @default.
• W4293195474 type Work @default.
• W4293195474 citedByCount "4" @default.
• W4293195474 countsByYear W42931954742023 @default.
• W4293195474 crossrefType "journal-article" @default.
• W4293195474 hasAuthorship W4293195474A5038619327 @default.
• W4293195474 hasAuthorship W4293195474A5063594676 @default.
• W4293195474 hasConcept C111919701 @default.
• W4293195474 hasConcept C113775141 @default.
• W4293195474 hasConcept C127162648 @default.
• W4293195474 hasConcept C148063708 @default.
• W4293195474 hasConcept C194739806 @default.
• W4293195474 hasConcept C2779960059 @default.
• W4293195474 hasConcept C2781430025 @default.
• W4293195474 hasConcept C31258907 @default.
• W4293195474 hasConcept C41008148 @default.
• W4293195474 hasConcept C555944384 @default.
• W4293195474 hasConcept C76155785 @default.
• W4293195474 hasConcept C79403827 @default.
• W4293195474 hasConcept C81978471 @default.
• W4293195474 hasConcept C9390403 @default.
• W4293195474 hasConcept C93996380 @default.
• W4293195474 hasConceptScore W4293195474C111919701 @default.
• W4293195474 hasConceptScore W4293195474C113775141 @default.
• W4293195474 hasConceptScore W4293195474C127162648 @default.
• W4293195474 hasConceptScore W4293195474C148063708 @default.
• W4293195474 hasConceptScore W4293195474C194739806 @default.
• W4293195474 hasConceptScore W4293195474C2779960059 @default.
• W4293195474 hasConceptScore W4293195474C2781430025 @default.
• W4293195474 hasConceptScore W4293195474C31258907 @default.
• W4293195474 hasConceptScore W4293195474C41008148 @default.
• W4293195474 hasConceptScore W4293195474C555944384 @default.
• W4293195474 hasConceptScore W4293195474C76155785 @default.
• W4293195474 hasConceptScore W4293195474C79403827 @default.
• W4293195474 hasConceptScore W4293195474C81978471 @default.
• W4293195474 hasConceptScore W4293195474C9390403 @default.
• W4293195474 hasConceptScore W4293195474C93996380 @default.
• W4293195474 hasFunder F4320306076 @default.
• W4293195474 hasIssue "11" @default.
• W4293195474 hasLocation W42931954741 @default.
• W4293195474 hasOpenAccess W4293195474 @default.
• W4293195474 hasPrimaryLocation W42931954741 @default.
• W4293195474 hasRelatedWork W2005406957 @default.
• W4293195474 hasRelatedWork W2024821657 @default.
• W4293195474 hasRelatedWork W2100039774 @default.
• W4293195474 hasRelatedWork W2123252081 @default.
• W4293195474 hasRelatedWork W2149108093 @default.
• W4293195474 hasRelatedWork W2382017388 @default.
• W4293195474 hasRelatedWork W3002441777 @default.
• W4293195474 hasRelatedWork W3183731658 @default.
• W4293195474 hasRelatedWork W4287068379 @default.
• W4293195474 hasRelatedWork W4289713079 @default.
• W4293195474 hasVolume "21" @default.
• W4293195474 isParatext "false" @default.
• W4293195474 isRetracted "false" @default.
• W4293195474 workType "article" @default.