Knowledge Distillation-Aided End-to-End Learning for Linear Precoding in Multiuser MIMO Downlink Systems with Finite-Rate Feedback

Kyeongbo Kong, Woo Jin Song, Moonsik Min

Research output: Contribution to journalArticlepeer-review

12 Scopus citations

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.

Original languageEnglish
Pages (from-to)11095-11100
Number of pages6
JournalIEEE Transactions on Vehicular Technology
Volume70
Issue number10
DOIs
StatePublished - 1 Oct 2021

Keywords

  • Deep learning
  • limited feedback
  • linear precoding
  • multiple-input multiple-output
  • spatial multiplexing

Fingerprint

Dive into the research topics of 'Knowledge Distillation-Aided End-to-End Learning for Linear Precoding in Multiuser MIMO Downlink Systems with Finite-Rate Feedback'. Together they form a unique fingerprint.

Cite this