On Training Neural Network Decoders of Rate Compatible Polar Codes via Transfer Learning

Abstract

Neural network decoders (NNDs) for rate-compatible polar codes are studied in this paper. We consider a family of rate-compatible polar codes which are constructed from a single polar coding sequence as defined by 5G new radios. We propose a transfer learning technique for training multiple NNDs of the rate-compatible polar codes utilizing their inclusion property. The trained NND for a low rate code is taken as the initial state of NND training for the next smallest rate code. The proposed method provides quicker training as compared to separate learning of the NNDs according to numerical results. We additionally show that an underfitting problem of NND training due to low model complexity can be solved by transfer learning techniques.

Security Gap Improvement of BICM Systems Through Bit-Labeling Optimization for the Gaussian Wiretap Channel

“…Jiang et al [228] A meta learning-based model independent neural decoder. Lee et al [229] Transfer learning for decoding a set of rate-compatible polar codes. Artemasov et al [230] A unified DL decoder for BCH and polar codes concatenated with CRC.…”

“…It has been demonstrated that the proposed scheme can adapt to a channel while achieving a performance close to that of a DL decoder designed solely for the particular channel. In the same line of research, the authors in [229] proposed transfer learning to efficiently train decoders for a set of rate-compatible polar codes that are expurgated from the same mother code as in 5G NR.…”