DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kong, Kyeongbo | - |
dc.contributor.author | Song, Woo-Jin | - |
dc.contributor.author | Min, Moonsik | - |
dc.date.accessioned | 2022-06-30T06:40:06Z | - |
dc.date.available | 2022-06-30T06:40:06Z | - |
dc.date.created | 2021-11-06 | - |
dc.date.issued | 2021-10 | - |
dc.identifier.issn | 0018-9545 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/113304 | - |
dc.description.abstract | We propose a deep learning-based channel estimation, quantization, feedback, and precoding method for downlink multiuser multiple-input and multiple-output systems. In the proposed system, channel estimation and quantization for limited feedback are handled by a receiver deep neural network (DNN). Precoder selection is handled by a transmitter DNN. To emulate the traditional channel quantization, a binarization layer is adopted at each receiver DNN, and the binarization layer is also used to enable end-to-end learning. However, this can lead to inaccurate gradients, which can trap the receiver DNNs at a poor local minimum during training. To address this, we consider knowledge distillation, in which the existing DNNs are jointly trained with an auxiliary transmitter DNN. The use of an auxiliary DNN as a teacher network allows the receiver DNNs to additionally exploit lossless gradients, which is useful in avoiding a poor local minimum. For the same number of feedback bits, our DNN-based precoding scheme can achieve a higher downlink rate compared to conventional linear precoding with codebook-based limited feedback. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY | - |
dc.title | Knowledge Distillation-Aided End-to-End Learning for Linear Precoding in Multiuser MIMO Downlink Systems With Finite-Rate Feedback | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/TVT.2021.3110608 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, v.70, no.10, pp.11095 - 11100 | - |
dc.identifier.wosid | 000707443200121 | - |
dc.citation.endPage | 11100 | - |
dc.citation.number | 10 | - |
dc.citation.startPage | 11095 | - |
dc.citation.title | IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY | - |
dc.citation.volume | 70 | - |
dc.contributor.affiliatedAuthor | Song, Woo-Jin | - |
dc.identifier.scopusid | 2-s2.0-85114733944 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.type.docType | Article | - |
dc.subject.keywordPlus | DESIGN | - |
dc.subject.keywordAuthor | Precoding | - |
dc.subject.keywordAuthor | Receivers | - |
dc.subject.keywordAuthor | Channel estimation | - |
dc.subject.keywordAuthor | Auxiliary transmitters | - |
dc.subject.keywordAuthor | Downlink | - |
dc.subject.keywordAuthor | MIMO communication | - |
dc.subject.keywordAuthor | Quantization (signal) | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | multiple-input multiple-output | - |
dc.subject.keywordAuthor | limited feedback | - |
dc.subject.keywordAuthor | spatial multiplexing | - |
dc.subject.keywordAuthor | linear precoding | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Transportation Science & Technology | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.