Evolving Token Communication with Parametric Memory Network

TL;DR

This paper introduces an evolving semantic token communication system using a parametric memory network over MIMO channels, reducing transmission costs and improving recovery accuracy through a novel token reconstruction approach.

Contribution

It proposes a new method combining truncated token transmission, a parametric memory network, and online evolution for efficient semantic communication over wireless channels.

Findings

Outperforms existing benchmarks under various channel conditions.

Achieves up to 1.09 dB PSNR improvement.

Effectively reconstructs full tokens from truncated prefixes.

Abstract

Token communication has emerged as a promising framework for efficient wireless transmission by representing source data as compact semantic tokens. However, transmitting full semantic tokens still incurs considerable communication overhead. In this paper, we propose an evolving semantic token communication system with a parametric memory network over MIMO fading channels. Specifically, only an equal-length prefix of each semantic token is transmitted, which reduces transmission cost while preserving a consistent token structure for receiver-side recovery. At the receiver, a parametric memory network is introduced to reconstruct the missing suffix information from the received token prefixes, where semantic memory is stored implicitly in the network parameters. To realize this design, full semantic tokens are first organized into a codebook, and truncated tokens are paired with the codeword labels of their corresponding full tokens. Based on these token-label pairs, kNN-based teacher distributions are constructed to fine-tune a pretrained GPT-2-based recovery module, which learns to infer the codeword distribution of each incomplete token and recover the corresponding complete semantic token. In addition, an online evolution strategy is developed to periodically update the parametric memory network and the entire system using newly observed test samples, thereby improving adaptability under distribution shifts. Experimental results demonstrate that the proposed method consistently outperforms the existing evolving memory benchmark under different channel conditions and channel bandwidth ratios, with up to 1.09 dB PSNR improvement.