Hyper-Graph-Network Decoders for Block Codes
arXiv:1909.09036
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.
Accepted to NeurIPS 2019. Camera Ready
Cited by in corpus (7)
- Personalized Federated Learning using Hypernetworks
- Learning the Pareto Front with Hypernetworks
- Molecule Property Prediction and Classification with Graph Hypernetworks
- On Infinite-Width Hypernetworks
- Autoregressive Belief Propagation for Decoding Block Codes
- Learning to Decode: Reinforcement Learning for Decoding of Sparse Graph-Based Channel Codes
- Self-Supervised Dynamic Networks for Covariate Shift Robustness