Deep Learning-based Polar Code Design
This addresses polar code design for communication systems, representing an incremental improvement through a novel method for a known bottleneck.
The paper tackles the problem of polar code construction by introducing a deep learning-based algorithm that treats information/frozen bit indices as trainable neural network weights, achieving considerable performance gains over state-of-the-art schemes for belief propagation decoding over AWGN and Rayleigh fading channels.
In this work, we introduce a deep learning-based polar code construction algorithm. The core idea is to represent the information/frozen bit indices of a polar code as a binary vector which can be interpreted as trainable weights of a neural network (NN). For this, we demonstrate how this binary vector can be relaxed to a soft-valued vector, facilitating the learning process through gradient descent and enabling an efficient code construction. We further show how different polar code design constraints (e.g., code rate) can be taken into account by means of careful binary-to-soft and soft-to-binary conversions, along with rate-adjustment after each learning iteration. Besides its conceptual simplicity, this approach benefits from having the "decoder-in-the-loop", i.e., the nature of the decoder is inherently taken into consideration while learning (designing) the polar code. We show results for belief propagation (BP) decoding over both AWGN and Rayleigh fading channels with considerable performance gains over state-of-the-art construction schemes.