Fibbinary-Based Compression and Quantization for Efficient Neural Radio Receivers

TL;DR

This paper proposes Fibonacci-based quantization and compression techniques to reduce the complexity and memory footprint of neural radio receivers, enabling efficient deployment on hardware-constrained devices while maintaining high performance.

Contribution

It introduces Fibonacci code word quantization, a novel incremental network quantization method, and two lossless compression algorithms tailored for Fibonacci quantized parameters, improving efficiency.

Findings

45 ext% power savings in multipliers

44 ext% area reduction in hardware

63.4 ext% memory footprint reduction

Abstract

Neural receivers have shown outstanding performance compared to the conventional ones but this comes with a high network complexity leading to a heavy computational cost. This poses significant challenges in their deployment on hardware-constrained devices. To address the issue, this paper explores two optimization strategies: quantization and compression. We introduce both uniform and non-uniform quantization such as the Fibonacci Code word Quantization (FCQ). A novel fine-grained approach to the Incremental Network Quantization (INQ) strategy is then proposed to compensate for the losses introduced by the above mentioned quantization techniques. Additionally, we introduce two novel lossless compression algorithms that effectively reduce the memory size by compressing sequences of Fibonacci quantized parameters characterized by a huge redundancy. The quantization technique provides a saving of 45\% and 44\% in the multiplier's power and area, respectively, and its combination with the compression determines a 63.4\% reduction in memory footprint, while still providing higher performances than a conventional receiver.