On Transfer Learning for a Fully Convolutional Deep Neural SIMO Receiver

TL;DR

This paper investigates transfer learning techniques for fully neural network-based SIMO wireless receivers, demonstrating that partial fine-tuning effectively adapts the system to different scenarios with limited data.

Contribution

It is the first study to apply transfer learning to an entire neural network-based receiver chain in wireless communication, exploring fine-tuning methods for various configuration mismatches.

Findings

Partial fine-tuning reduces performance gap more effectively.

Transfer learning enables adaptation with smaller datasets.

Simulation confirms improved performance with fine-tuning.

Abstract

Deep learning has been used to tackle problems in wireless communication including signal detection, channel estimation, traffic prediction, and demapping. Achieving reasonable results with deep learning typically requires large datasets which may be difficult to obtain for every scenario/configuration in wireless communication. Transfer learning (TL) solves this problem by leveraging knowledge and experience gained from one scenario or configuration to adapt a system to a different scenario using smaller dataset. TL has been studied for various stand-alone parts of the radio receiver where individual receiver components, for example, the channel estimator are replaced by a neural network. There has however been no work on TL for receivers where the entire receiver chain is replaced by a neural network. This paper fills this gap by studying the performance of fine-tuning based transfer learning techniques for various configuration mismatch cases using a deep neural single-input-multiple-output(SIMO) receiver. Simulation results show that overall, partial fine-tuning better closes the performance gap between zero target dataset and sufficient target dataset.