# End-to-End Autoencoder Communications with Optimized Interference Suppression

arXiv: https://arxiv.org/abs/2201.01388 · HTML: https://mlsanity.com/paper/2201.01388/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 29 Dec 2021.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management](https://mlsanity.com/paper/1705.09412/) (2017)
- [Deep Learning-Based Communication Over the Air](https://mlsanity.com/paper/1707.03384/) (2017)
- [Deep Learning for Wireless Communications](https://mlsanity.com/paper/2005.06068/) (2020)
- [High Dimensional Channel Estimation Using Deep Generative Networks](https://mlsanity.com/paper/2006.13494/) (2020)
- [Deep Learning for Launching and Mitigating Wireless Jamming Attacks](https://mlsanity.com/paper/1807.02567/) (2018)
- [OFDM-Autoencoder for End-to-End Learning of Communications Systems](https://mlsanity.com/paper/1803.05815/) (2018)
- [Approximating the Void: Learning Stochastic Channel Models from Observation with Variational Generative Adversarial Networks](https://mlsanity.com/paper/1805.06350/) (2018)
- [Generative Adversarial Network for Wireless Signal Spoofing](https://mlsanity.com/paper/1905.01008/) (2019)
- [Wideband Channel Estimation with A Generative Adversarial Network](https://mlsanity.com/paper/2012.12063/) (2020)
- [Generative Adversarial Learning for Spectrum Sensing](https://mlsanity.com/paper/1804.00709/) (2018)
- [Interference Suppression Using Deep Learning: Current Approaches and Open Challenges](https://mlsanity.com/paper/2112.08988/) (2021)
- [Real-Time and Embedded Deep Learning on FPGA for RF Signal Classification](https://mlsanity.com/paper/1910.05765/) (2019)
- [Trimming the Fat from OFDM: Pilot- and CP-less Communication with End-to-end Learning](https://mlsanity.com/paper/2101.08213/) (2021)
- [End-to-End Learning of OFDM Waveforms with PAPR and ACLR Constraints](https://mlsanity.com/paper/2106.16039/) (2021)
- [Benchmarking End-to-end Learning of MIMO Physical-Layer Communication](https://mlsanity.com/paper/2005.09718/) (2020)
- [Two-Timescale End-to-End Learning for Channel Acquisition and Hybrid Precoding](https://mlsanity.com/paper/2110.12059/) (2021)
- [Autoencoder-based Communications with Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2112.04441/) (2021)
- [Capacity-Approaching Autoencoders for Communications](https://mlsanity.com/paper/2009.05273/) (2020)

## Built on by (most cited first, 2 of 2)

- [Machine Learning in NextG Networks via Generative Adversarial Networks](https://mlsanity.com/paper/2203.04453/) (2022)
- [Sensing-Throughput Tradeoffs with Generative Adversarial Networks for NextG Spectrum Sharing](https://mlsanity.com/paper/2212.13598/) (2022)

## Abstract (arXiv)

An end-to-end communications system based on Orthogonal Frequency Division Multiplexing (OFDM) is modeled as an autoencoder (AE) for which the transmitter (coding and modulation) and receiver (demodulation and decoding) are represented as deep neural networks (DNNs) of the encoder and decoder, respectively. This AE communications approach is shown to outperform conventional communications in terms of bit error rate (BER) under practical scenarios regarding channel and interference effects as well as training data and embedded implementation constraints. A generative adversarial network (GAN) is trained to augment the training data when there is not enough training data available. Also, the performance is evaluated in terms of the DNN model quantization and the corresponding memory requirements for embedded implementation. Then, interference training and randomized smoothing are introduced to train the AE communications to operate under unknown and dynamic interference (jamming) effects on potentially multiple OFDM symbols. Relative to conventional communications, up to 36 dB interference suppression for a channel reuse of four can be achieved by the AE communications with interference training and randomized smoothing. AE communications is also extended to the multiple-input multiple-output (MIMO) case and its BER performance gain with and without interference effects is demonstrated compared to conventional MIMO communications.