Reproduce “Neural Enhanced Belief Propagation on Factor Graphs” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Victor Garcia Satorras, Max Welling
Neural Enhanced Belief Propagation (NEBP) refines low-density parity-check decoding when channel noise differs from its assumed model. It retains belief propagation and uses a graph neural network to correct its messages. In simulations with one code, NEBP is more robust as burst noise grows and stays close to LDPC on Gaussian noise; these results do not establish performance on other channels or codes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.