US 2023/0403100 A1 · GRAPH NEURAL NETWORK FOR CHANNEL DECODING

Abstract

Various embodiments and implementations of graph-neural-network (GNN)-based decoding applications are disclosed. The GNN-based decoding schemes are broadly applicable to different coding schemes, and capable of operating on both binary and non-binary codewords, in different implementations. Advantageously, the inventive GNN-based decoding is scalable, even with arbitrary block lengths, and not subject to typical limits with respect to dimensionality. Decoding performance of the inventive GNN-based techniques demonstrably matches or outpaces BCH and LDPC (both regular and 5G NR) decoding algorithms, while exhibiting improvements with respect to number of iterations required and scalability of the GNN-based approach. These inventive concepts are implemented, according to various embodiments, as methods, systems, and computer program products.

Claims26

Dependent claims

A method, comprising:

at a device:
receiving one or more codewords of a linear block code;
embedding the one or more received codewords into a higher-dimensional space;
and
decoding the embedded codeword(s) using a graph neural network (GNN)-based decoder trained to decode linear block codes of arbitrary block length.

2 more elements

A system, comprising:

a non-transitory memory storage comprising instructions;
and
one or more processors in communication with the memory, wherein the one or more processors execute the instructions to:
receive one or more codewords of a linear block code;
embed the one or more received codewords into a higher-dimensional space;
and
decode the embedded codewords using a graph neural network (GNN)-based decoder trained to decode linear block codes of arbitrary block length.

4 more elements

A non-transitory computer readable media storing computer instructions which, when executed by one or more processors of a device, cause the device to:

receive codewords of a linear block code;
embed the received codewords into a higher-dimensional space;
and
decode the said embedded codewords using a graph neural network (GNN)-based decoder trained to decode linear block codes of arbitrary block length.

1 more element

Dependencies are inferred from the claim text.

Facts

Application

18/118,637Filed 7 Mar 2023

Priority

14 Jun 2022

Published

14 Dec 2023

Term ends

Not estimatedThe source records don’t support an estimate.

Classification10 codes

H04L 1/0054
Arrangements at the receiver end: maximum-likelihood or sequential decoding, e.g. Viterbi, Fano, ZJ algorithms
G06N 3/04
Neural networks: architecture, e.g. interconnection topology
G06N 3/042
Architecture, e.g. interconnection topology: knowledge-based neural networks; Logical representations of neural networks
G06N 3/0455
Combinations of networks: auto-encoder networks; Encoder-decoder networks

Graph neural network for channel decoding

Life of this patent

Graph neural network for channel decoding

Life of this patent

Abstract

Claims26