Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289446335> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4289446335 abstract "In this work, we propose a fully differentiable graph neural network (GNN)-based architecture for channel decoding and showcase a competitive decoding performance for various coding schemes, such as low-density parity-check (LDPC) and BCH codes. The idea is to let a neural network (NN) learn a generalized message passing algorithm over a given graph that represents the forward error correction (FEC) code structure by replacing node and edge message updates with trainable functions. Contrary to many other deep learning-based decoding approaches, the proposed solution enjoys scalability to arbitrary block lengths and the training is not limited by the curse of dimensionality. We benchmark our proposed decoder against state-of-the-art in conventional channel decoding as well as against recent deep learning-based results. For the (63,45) BCH code, our solution outperforms weighted belief propagation (BP) decoding by approximately 0.4 dB with significantly less decoding iterations and even for 5G NR LDPC codes, we observe a competitive performance when compared to conventional BP decoding. For the BCH codes, the resulting GNN decoder can be fully parametrized with only 9640 weights." @default.
- W4289446335 created "2022-08-02" @default.
- W4289446335 creator A5004577729 @default.
- W4289446335 creator A5007637457 @default.
- W4289446335 creator A5018506109 @default.
- W4289446335 creator A5074728359 @default.
- W4289446335 date "2022-07-29" @default.
- W4289446335 modified "2023-09-27" @default.
- W4289446335 title "Graph Neural Networks for Channel Decoding" @default.
- W4289446335 doi "https://doi.org/10.48550/arxiv.2207.14742" @default.
- W4289446335 hasPublicationYear "2022" @default.
- W4289446335 type Work @default.
- W4289446335 citedByCount "0" @default.
- W4289446335 crossrefType "posted-content" @default.
- W4289446335 hasAuthorship W4289446335A5004577729 @default.
- W4289446335 hasAuthorship W4289446335A5007637457 @default.
- W4289446335 hasAuthorship W4289446335A5018506109 @default.
- W4289446335 hasAuthorship W4289446335A5074728359 @default.
- W4289446335 hasBestOaLocation W42894463351 @default.
- W4289446335 hasConcept C11413529 @default.
- W4289446335 hasConcept C132727834 @default.
- W4289446335 hasConcept C13280743 @default.
- W4289446335 hasConcept C152948882 @default.
- W4289446335 hasConcept C157125643 @default.
- W4289446335 hasConcept C185798385 @default.
- W4289446335 hasConcept C193969084 @default.
- W4289446335 hasConcept C204397858 @default.
- W4289446335 hasConcept C205649164 @default.
- W4289446335 hasConcept C41008148 @default.
- W4289446335 hasConcept C42276685 @default.
- W4289446335 hasConcept C57273362 @default.
- W4289446335 hasConcept C67692717 @default.
- W4289446335 hasConcept C78944582 @default.
- W4289446335 hasConcept C80444323 @default.
- W4289446335 hasConceptScore W4289446335C11413529 @default.
- W4289446335 hasConceptScore W4289446335C132727834 @default.
- W4289446335 hasConceptScore W4289446335C13280743 @default.
- W4289446335 hasConceptScore W4289446335C152948882 @default.
- W4289446335 hasConceptScore W4289446335C157125643 @default.
- W4289446335 hasConceptScore W4289446335C185798385 @default.
- W4289446335 hasConceptScore W4289446335C193969084 @default.
- W4289446335 hasConceptScore W4289446335C204397858 @default.
- W4289446335 hasConceptScore W4289446335C205649164 @default.
- W4289446335 hasConceptScore W4289446335C41008148 @default.
- W4289446335 hasConceptScore W4289446335C42276685 @default.
- W4289446335 hasConceptScore W4289446335C57273362 @default.
- W4289446335 hasConceptScore W4289446335C67692717 @default.
- W4289446335 hasConceptScore W4289446335C78944582 @default.
- W4289446335 hasConceptScore W4289446335C80444323 @default.
- W4289446335 hasLocation W42894463351 @default.
- W4289446335 hasOpenAccess W4289446335 @default.
- W4289446335 hasPrimaryLocation W42894463351 @default.
- W4289446335 hasRelatedWork W2010303399 @default.
- W4289446335 hasRelatedWork W2041362683 @default.
- W4289446335 hasRelatedWork W2060592722 @default.
- W4289446335 hasRelatedWork W2118148379 @default.
- W4289446335 hasRelatedWork W2135229457 @default.
- W4289446335 hasRelatedWork W2135938714 @default.
- W4289446335 hasRelatedWork W2155783837 @default.
- W4289446335 hasRelatedWork W2372732308 @default.
- W4289446335 hasRelatedWork W2591644370 @default.
- W4289446335 hasRelatedWork W3213661334 @default.
- W4289446335 isParatext "false" @default.
- W4289446335 isRetracted "false" @default.
- W4289446335 workType "article" @default.