Pruning and Quantizing Neural Belief Propagation Decoders
Pruning and Quantizing Neural Belief Propagation Decoders
复制标题
修剪和量化神经置信传播解码器
DOI：
10.1109/jsac.2020.3041392
复制
发表时间：
2020
影响因子：
16.4
通讯作者：
A. Graell i Amat
中科院分区：
文献类型：
--
作者：
Andreas Buchberger;Christian Häger;H. Pfister;L. Schmalen;A. Graell i Amat
我们考虑短线性分组码的近最大似然（ML）解码。特别是，我们提出了一种新的解码方法的基础上，神经信念传播（NBP）解码最近介绍了Nachmani等人。在其中，我们允许在算法的每次迭代不同的奇偶校验矩阵。其关键思想是考虑NBP解码过完备奇偶校验矩阵和使用的权重NBP作为衡量的重要性的检查节点（CN）的解码。然后修剪不重要的CN。与在给定的固定奇偶校验矩阵上执行解码的NBP相比，所提出的基于修剪的神经置信传播（PB-NBP）通常在每次迭代中导致不同的奇偶校验矩阵。对于一个给定的复杂性CN的评价，我们表明，PB-NBP产生显着的性能改善相对于NBP。我们将所提出的解码器应用于Reed-Muller码、短低密度奇偶校验（LDPC）码和极化码的解码。PB-NBP在过完备奇偶校验矩阵上优于NBP解码0.27-0.31 dB，同时将所需CN评估的数量减少高达97%。对于LDPC码，PB-NBP比具有相同数量的CN评估的常规置信传播好0.52dB。我们进一步扩展修剪的概念，偏移最小和解码，并引入一个修剪为基础的神经偏移最小和（PB-NOMS）解码器，我们共同优化的偏移量和量化的消息和偏移。我们证明性能0.5 dB ML解码与5位量化的Reed-Muller码。
We consider near maximum-likelihood (ML) decoding of short linear block codes. In particular, we propose a novel decoding approach based on neural belief propagation (NBP) decoding recently introduced by Nachmani et al. in which we allow a different parity-check matrix in each iteration of the algorithm. The key idea is to consider NBP decoding over an overcomplete parity-check matrix and use the weights of NBP as a measure of the importance of the check nodes (CNs) to decoding. The unimportant CNs are then pruned. In contrast to NBP, which performs decoding on a given fixed parity-check matrix, the proposed pruning-based neural belief propagation (PB-NBP) typically results in a different parity-check matrix in each iteration. For a given complexity in terms of CN evaluations, we show that PB-NBP yields significant performance improvements with respect to NBP. We apply the proposed decoder to the decoding of a Reed-Muller code, a short low-density parity-check (LDPC) code, and a polar code. PB-NBP outperforms NBP decoding over an overcomplete parity-check matrix by 0.27–0.31 dB while reducing the number of required CN evaluations by up to 97%. For the LDPC code, PB-NBP outperforms conventional belief propagation with the same number of CN evaluations by 0.52 dB. We further extend the pruning concept to offset min-sum decoding and introduce a pruning-based neural offset min-sum (PB-NOMS) decoder, for which we jointly optimize the offsets and the quantization of the messages and offsets. We demonstrate performance 0.5 dB from ML decoding with 5-bit quantization for the Reed-Muller code.
DOI：
10.1109/isit.2019.8849419
发表时间：
2019-01
期刊：
2019 IEEE International Symposium on Information Theory (ISIT)
影响因子：
--
作者：
Mengke Lian;Fabrizio Carpi;Christian Häger;H. Pfister
通讯作者：
Mengke Lian;Fabrizio Carpi;Christian Häger;H. Pfister