Learning to Communicate: Channel Auto-encoders, Domain Specific Regularizers, and Attention

TL;DR

This paper proposes a novel channel autoencoder architecture with domain-specific regularizers and attention mechanisms to improve communication over impaired channels, demonstrating promising initial capacity results.

Contribution

It introduces new regularizing layers and an attention-based decoder to enhance adaptive communication over noisy channels, advancing the design of learned communication systems.

Findings

Initial capacity results show promise for the proposed architecture.

Domain-specific regularizers effectively emulate channel impairments.

Attention mechanisms aid in recovering canonical signal representations.

Abstract

We address the problem of learning efficient and adaptive ways to communicate binary information over an impaired channel. We treat the problem as reconstruction optimization through impairment layers in a channel autoencoder and introduce several new domain-specific regularizing layers to emulate common channel impairments. We also apply a radio transformer network based attention model on the input of the decoder to help recover canonical signal representations. We demonstrate some promising initial capacity results from this architecture and address several remaining challenges before such a system could become practical.