Hyper-Graph-Network Decoders for Block Codes
From MaRDI portal
Publication:6325626
arXiv1909.09036MaRDI QIDQ6325626
Author name not available (Why is that?)
Publication date: 5 September 2019
Abstract: Neural decoders were shown to outperform classical message passing techniques for short BCH codes. In this work, we extend these results to much larger families of algebraic block codes, by performing message passing with graph neural networks. The parameters of the sub-network at each variable-node in the Tanner graph are obtained from a hypernetwork that receives the absolute values of the current message as input. To add stability, we employ a simplified version of the arctanh activation that is based on a high order Taylor approximation of this activation function. Our results show that for a large number of algebraic block codes, from diverse families of codes (BCH, LDPC, Polar), the decoding obtained with our method outperforms the vanilla belief propagation method as well as other learning techniques from the literature.
Has companion code repository: https://github.com/facebookresearch/HyperNetworkDecoder
This page was built for publication: Hyper-Graph-Network Decoders for Block Codes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6325626)
