Attention-Empowered Residual Autoencoder for End-to-End Communication Systems
Authors:
- 10 February 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 27 (4) , 1140-1144
Abstract
Channel autoencoders adopt neural networks to represent and optimize previous block-driven communication systems from an end-to-end perspective. The existing deep fully connected autoencoder needs retraining when the input length of bit sequences changes since it can only handle fixed-length data. Convolutional neural network (CNN)-based autoencoder can accept arbitrary lengths and is widely adopted. But it has limitations in 1) error floor in high signal-to-noise ratio (SNR) regions, and 2) poor performance against interference. Therefore, we first adopt a residual attention module to enhance the representation ability of the autoencoder, where channel and spatial attention focus on finding fine-grained clues between signals and noise. An adaptive data-flow merging scheme for demapper is further proposed to satisfy dynamic environments. Simulation results show that the proposed method can achieve great gains in coded and uncoded transmission scenarios. Our method is robust and generalizable against error floor and burst interference, as compared to a conventional system.Keywords
Funding Information
- National Key Research & Development (R&D) Program of China (2022YFB3206800)
This publication has 12 references indexed in Scilit:
- A Markovian Model-Driven Deep Learning Framework for Massive MIMO CSI FeedbackIEEE Transactions on Wireless Communications, 2021
- A Survey of Modulation Classification Using Deep Learning: Signal Representation and Data PreprocessingIEEE Transactions on Neural Networks and Learning Systems, 2021
- Channel Autoencoder for Wireless Communication: State of the Art, Challenges, and TrendsIEEE Communications Magazine, 2021
- Trainable Communication Systems: Concepts and PrototypeIEEE Transactions on Communications, 2020
- An Efficient Deep Learning Framework for Low Rate Massive MIMO CSI ReportingIEEE Transactions on Communications, 2020
- ConvAE: A New Channel Autoencoder Based on Convolutional Layers and Residual ConnectionsIEEE Communications Letters, 2019
- A CNN-Based End-to-End Learning Framework Toward Intelligent Communication SystemsIEEE Access, 2019
- Joint Transceiver Optimization for Wireless Communication PHY Using Neural NetworkIEEE Journal on Selected Areas in Communications, 2019
- An Introduction to Deep Learning for the Physical LayerIEEE Transactions on Cognitive Communications and Networking, 2017
- Deep Residual Learning for Image Recognition2016