5G LDPC Linear Transformer for Channel Decoding
This addresses the need for efficient channel decoding in 5G communications, offering a scalable solution with reduced complexity, though it is incremental as it builds on existing transformer and BP methods.
The paper tackles the problem of decoding 5G LDPC codes by introducing a novel linear-time complexity transformer decoder, achieving bit error rate performance that matches regular transformers and surpasses one iteration of Belief Propagation, with competitive time performance for larger block codes.
This work introduces a novel, fully differentiable linear-time complexity transformer decoder and a transformer decoder to correct 5G New Radio (NR) LDPC. We propose a scalable approach to decode linear block codes with $O(n)$ complexity rather than $O(n^2)$ for regular transformers. The architectures' performances are compared to Belief Propagation (BP), the production-level decoding algorithm used for 5G New Radio (NR) LDPC codes. We achieve bit error rate performance that matches a regular Transformer decoder and surpases one iteration BP, also achieving competitive time performance against BP, even for larger block codes. We utilize Sionna, Nvidia's 5G & 6G physical layer research software, for reproducible results.