Unsupervised Learning for Neural Network-based Polar Decoder via Syndrome Loss
This work addresses the challenge of channel variations in communication systems by enabling unsupervised learning for polar decoders, though it is incremental as it adapts an existing method to a specific code structure.
The paper tackles the problem of needing massive labeled data for supervised learning in neural network-based polar decoders by proposing a modified syndrome loss that enables unsupervised learning, demonstrating through simulations that domain-specific knowledge can achieve this.
With the rapid growth of deep learning in many fields, machine learning-assisted communication systems had attracted lots of researches with many eye-catching initial results. At the present stage, most of the methods still have great demand of massive labeled data for supervised learning. However, obtaining labeled data in the practical applications is not feasible, which may result in severe performance degradation due to channel variations. To overcome such a constraint, syndrome loss has been proposed to penalize non-valid decoded codewords and achieve unsupervised learning for neural network-based decoder. However, it cannot be applied to polar decoder directly. In this work, by exploiting the nature of polar codes, we propose a modified syndrome loss. From simulation results, the proposed method demonstrates that domain-specific knowledge and know-how in code structure can enable unsupervised learning for neural network-based polar decoder.