← Back to all news
arXiv AI By Samira Malek

Learning to Decode Linear Codes with Generalized Belief Propagation Network

Read the original on arXiv AI →

The paper introduces GBPNet, a Generalized Belief Propagation Network that maintains message‑passing symmetry while improving learning capability for decoding linear codes. GBPNet employs cascaded variable‑node updates and learned element‑wise message scaling, preserving the Tanner graph structure. Two training strategies—progressive training and high‑SNR training—are proposed, and experiments show GBPNet achieves lower bit error rates than conventional belief propagation and other state‑of‑the‑art neural decoders.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Oct 28

Joint End-to-End Training of Weighted BP Decoder Ensembles

The paper presents a method for jointly training an ensemble of weighted belief‑propagation decoders by optimizing trainable Tanner‑graph edge weights. Four ensemble objectives are compared, and best‑member training is found to be most effective. On a (64,32) PEG LDPC code, the ensemble achieves a 0.66 dB gain over a single decoder at FER = 10⁻⁴, and similar improvements are seen on a (128,64) CCSDS LDPC code, demonstrating learned complementary failure events rather than uniformly better components.

By Felix Krieg, Paul Bezner, Stephan ten Brink
More like this →
arXiv Machine Learning
Oct 23

On the Adversarial Vulnerability of Neural Receivers with Unrolled LDPC Decoders

The paper investigates the adversarial vulnerability of neural receivers that incorporate unrolled LDPC decoders for 5G NR. It finds that standard gradient-based attacks are ineffective due to gradient masking caused by tanh saturation in the BP check-node update, leading to a dramatic decay in gradient norm over iterations. To overcome this, the authors propose two loss functions—L_BP and L_LLR—that restore attack efficacy, significantly increasing block-error rates across different neural receiver implementations.

By Aakash Saini, Jafar Aco Mohammadi, Wolfgang Gerstacker
safety
More like this →
arXiv Machine Learning
Aug 28

Leveraging Code Automorphisms for Improved Syndrome-Based Neural Decoding

The paper demonstrates that incorporating code automorphisms into syndrome-based neural decoding (SBND) improves the models’ learning and generalization through data augmentation during training and inference. By applying this technique to short, high-rate codes, the authors achieve performance close to maximum likelihood decoding (MLD) using small datasets and appropriate training. The study also indicates that previous SBND results may have underestimated their true error‑correction capability due to insufficient training.

By Rapha\"el Le Bidan, Ahmad Ismail, Elsa Dupraz, Charbel Abdel Nour
More like this →