Semantic Packet Aggregation for Token Communication via Genetic Beam Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Seunghun, Park, Jihong, Choi, Jinho, Park, Hyuncheol
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913810336448512
author Lee, Seunghun
Park, Jihong
Choi, Jinho
Park, Hyuncheol
author_facet Lee, Seunghun
Park, Jihong
Choi, Jinho
Park, Hyuncheol
contents Token communication (TC) is poised to play a pivotal role in emerging language-driven applications such as AI-generated content (AIGC) and wireless language models (LLMs). However, token loss caused by channel noise can severely degrade task performance. To address this, in this article, we focus on the problem of semantics-aware packetization and develop a novel algorithm, termed semantic packet aggregation with genetic beam search (SemPA-GBeam), which aims to maximize the average token similarity (ATS) over erasure channels. Inspired from the genetic algorithm (GA) and the beam search algorithm, SemPA-GBeam iteratively optimizes token grouping for packetization within a fixed number of groups (i.e., fixed beam width in beam search) while randomly swapping a fraction of tokens (i.e., mutation in GA). Experiments on the MS-COCO dataset demonstrate that SemPA-GBeam achieves ATS and LPIPS scores comparable to exhaustive search while reducing complexity by more than 20x.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19591
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Semantic Packet Aggregation for Token Communication via Genetic Beam Search
Lee, Seunghun
Park, Jihong
Choi, Jinho
Park, Hyuncheol
Signal Processing
Token communication (TC) is poised to play a pivotal role in emerging language-driven applications such as AI-generated content (AIGC) and wireless language models (LLMs). However, token loss caused by channel noise can severely degrade task performance. To address this, in this article, we focus on the problem of semantics-aware packetization and develop a novel algorithm, termed semantic packet aggregation with genetic beam search (SemPA-GBeam), which aims to maximize the average token similarity (ATS) over erasure channels. Inspired from the genetic algorithm (GA) and the beam search algorithm, SemPA-GBeam iteratively optimizes token grouping for packetization within a fixed number of groups (i.e., fixed beam width in beam search) while randomly swapping a fraction of tokens (i.e., mutation in GA). Experiments on the MS-COCO dataset demonstrate that SemPA-GBeam achieves ATS and LPIPS scores comparable to exhaustive search while reducing complexity by more than 20x.
title Semantic Packet Aggregation for Token Communication via Genetic Beam Search
topic Signal Processing
url https://arxiv.org/abs/2504.19591