A Study of Neural Polar Decoders for Communication

2025-10-03

AI Summary

To address the limitations of neural polar decoders (NPDs) in adapting to arbitrary code lengths, high-order modulation, and time-varying channels with memory—common in practical communication systems—this paper proposes an end-to-end trainable neural polar decoding architecture. The architecture explicitly models channel statistics and memory structure via neural networks, enabling pilot-free, cyclic-prefix-free joint single-carrier and OFDM transmission while supporting rate matching and high-order modulation. Its key innovation lies in the first explicit incorporation of channel memory into NPD design, enabling accurate modeling of typical 5G fading channels and low-PAPR efficient transmission. Experimental results demonstrate that, under short-code and low-rate regimes, the proposed scheme significantly outperforms the standard 5G polar decoder: block error rates are reduced by one to two orders of magnitude, throughput increases by 15–30%, and single-carrier performance matches OFDM while achieving lower peak-to-average power ratio.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

In this paper, we adapt and analyze Neural Polar Decoders (NPDs) for end-to-end communication systems. While prior work demonstrated the effectiveness of NPDs on synthetic channels, this study extends the NPD to real-world communication systems. The NPD was adapted to complete OFDM and single-carrier communication systems. To satisfy practical system requirements, the NPD is extended to support any code length via rate matching, higher-order modulations, and robustness across diverse channel conditions. The NPD operates directly on channels with memory, exploiting their structure to achieve higher data rates without requiring pilots and a cyclic prefix. Although NPD entails higher computational complexity than the standard 5G polar decoder, its neural network architecture enables an efficient representation of channel statistics, resulting in manageable complexity suitable for practical systems. Experimental results over 5G channels demonstrate that the NPD consistently outperforms the 5G polar decoder in terms of BER, BLER, and throughput. These improvements are particularly significant for low-rate and short-block configurations, which are prevalent in 5G control channels. Furthermore, NPDs applied to single-carrier systems offer performance comparable to OFDM with lower PAPR, enabling effective single-carrier transmission over 5G channels. These results position the NPD as a high-performance, pilotless, and robust decoding solution.

Problem

• Adapting Neural Polar Decoders to real-world communication systems
• Extending NPD to support variable code lengths and modulations
• Enhancing decoding performance without pilots in 5G channels

Innovation

• Neural Polar Decoders adapted for real-world communication systems
• Extended to support any code length and higher-order modulations
• Operates directly on channels with memory without pilots