Achieving Low Complexity Neural Decoders via Iterative Pruning

TL;DR

This paper explores iterative pruning techniques to reduce the complexity of neural decoders, making them more suitable for edge devices while maintaining accuracy, and introduces semi-soft decision decoding to enhance performance.

Contribution

It introduces a pruning approach based on the lottery ticket hypothesis for neural decoders and proposes semi-soft decision decoding to improve bit error rate performance.

Findings

Pruned neural decoders retain accuracy with fewer weights.

Pruning reduces latency and computational complexity.

Semi-soft decoding improves bit error rate performance.

Abstract

The advancement of deep learning has led to the development of neural decoders for low latency communications. However, neural decoders can be very complex which can lead to increased computation and latency. We consider iterative pruning approaches (such as the lottery ticket hypothesis algorithm) to prune weights in neural decoders. Decoders with fewer number of weights can have lower latency and lower complexity while retaining the accuracy of the original model. This will make neural decoders more suitable for mobile and other edge devices with limited computational power. We also propose semi-soft decision decoding for neural decoders which can be used to improve the bit error rate performance of the pruned network.