Learning Robust Representations for Communications over Interference-limited Channels

TL;DR

This paper introduces autoencoder-based models, TwinNet and SiameseNet, for interference-limited communication channels, demonstrating their ability to outperform traditional methods by leveraging interference structure.

Contribution

The paper proposes two novel autoencoder architectures, TwinNet and SiameseNet, tailored for interference-limited channels, and provides analysis of their performance and codeword characteristics.

Findings

Models outperform traditional orthogonal methods.

Quantifiable advantages in specific interference scenarios.

Analysis of codeword structures reveals how models achieve better performance.

Abstract

In the context of cellular networks, users located at the periphery of cells are particularly vulnerable to substantial interference from neighbouring cells, which can be represented as a two-user interference channel. This study introduces two highly effective methodologies, namely TwinNet and SiameseNet, using autoencoders, tailored for the design of encoders and decoders for block transmission and detection in interference-limited environments. The findings unambiguously illustrate that the developed models are capable of leveraging the interference structure to outperform traditional methods reliant on complete orthogonality. While it is recognized that systems employing coordinated transmissions and independent detection can offer greater capacity, the specific gains of data-driven models have not been thoroughly quantified or elucidated. This paper conducts an analysis to demonstrate the quantifiable advantages of such models in particular scenarios. Additionally, a comprehensive examination of the characteristics of codewords generated by these models is provided to offer a more intuitive comprehension of how these models achieve superior performance.