Semantics-Aware Hierarchical Token Communication: Clustering, Bit Mapping, and Power Allocation

TL;DR

This paper introduces H-TokCom, a hierarchical token communication framework that embeds semantic structure into physical-layer design, improving semantic robustness over traditional approaches especially at low SNR.

Contribution

It proposes a novel hierarchical token communication scheme that clusters semantically similar tokens and allocates power accordingly to reduce semantic loss.

Findings

H-TokCom increases semantic similarity from 0.206 to 0.279 at 3 dB SNR on COCO.

Hierarchical design improves robustness against errors within semantic clusters.

Power allocation to cluster prefixes enhances semantic preservation.

Abstract

Despite the rise of token communication (TokCom) as a new paradigm beyond traditional bit communication, existing approaches have primarily adopted artificial intelligence (AI)-centric designs that rely on semantic recovery via large models. Meanwhile, their physical-layer designs, such as token-bit mapping and power allocation, remain conventional and do not reflect token-level semantics. These semantics-agnostic designs can lead to significant semantic loss, particularly at low signal-to-noise ratio (SNR) levels. To address this issue, we propose hierarchical TokCom (H-TokCom), a framework that embeds semantic structure directly into physical-layer design. The key idea is to group semantically similar tokens into clusters and hierarchically assign their bit representations, where each token is represented by a cluster-level prefix and a token-specific suffix. As long as the cluster bits are correctly delivered, errors in the suffix bits typically map the received token to another within the same semantic cluster, resulting in only limited semantic distortion. This robustness is further strengthened by allocating more transmit power to the prefix bits than to the suffix bits. Simulation results show that H-TokCom achieves substantial semantic-similarity gains over conventional TokCom across the considered SNR range, increasing the semantic similarity from $0.206$ to $0.279$ at $\gamma=3$ dB on COCO, corresponding to a gain of $0.073$ $(35.4\%)$.