For One-Shot Decoding: Self-supervised Deep Learning-Based Polar Decoder
This work addresses decoding efficiency in communication systems, offering a novel self-supervised approach that is incremental in improving applicability and performance for polar codes.
The paper tackles the problem of decoding polar codes by proposing a self-supervised deep learning-based scheme that enables one-shot decoding, eliminating the need for predefined labels and allowing training on actual communication data. The results show that the bit error rate and block error rate performances approach those of the maximum a posteriori decoder for very short packets, and the neural network decoder exhibits superior generalization ability compared to conventional methods.
We propose a self-supervised deep learning-based decoding scheme that enables one-shot decoding of polar codes. In the proposed scheme, rather than using the information bit vectors as labels for training the neural network (NN) through supervised learning as the conventional scheme did, the NN is trained to function as a bounded distance decoder by leveraging the generator matrix of polar codes through self-supervised learning. This approach eliminates the reliance on predefined labels, empowering the potential to train directly on the actual data within communication systems and thereby enhancing the applicability. Furthermore, computer simulations demonstrate that (i) the bit error rate (BER) and block error rate (BLER) performances of the proposed scheme can approach those of the maximum a posteriori (MAP) decoder for very short packets and (ii) the proposed NN decoder (NND) exhibits much superior generalization ability compared to the conventional one.