缩小语义-边缘差距：面向6G无线智能的微型语言模型
Closing the Semantic-Edge Gap: Tiny Language Models for 6G Wireless Intelligence
浏览论文内容
中文总结 AI 辅助
本综述针对6G语义通信中LLM不适用于边缘设备的问题，通过两轴分类法关联TinyML压缩技术与语义通信架构，结合定量分析验证了相关方案的性能，明确了九大开放挑战。
中文摘要 AI 辅助
第六代（6G）无线网络被设想为AI原生系统，其中语义通信——传输任务相关的意义而非原始比特——超越了香农的经典比特管道模型。大型语言模型（LLM）主导语义编码，但由于内存、能耗和延迟成本过高，不适用于6G用户设备和物联网设备。微型语言模型（TinyLM）通过微型机器学习（TinyML）技术压缩至千字节至兆字节内存和毫瓦级功耗预算，是连接LLM级语义编码与6G边缘硬件的缺失桥梁，但此前无研究系统地将TinyML技术映射到语义通信架构以实现此目标。本综述通过两轴分类法缩小该差距，将六大压缩家族（量化、剪枝、知识蒸馏、低秩适配、神经架构搜索、混合流水线）与五大语义通信架构（端到端联合信源信道编码、联邦学习、知识图谱辅助、多任务/跨模态通信）关联，并结合模型规模与语义保真度帕累托前沿的定量元分析。代表性结果包括：CNN-Transformer编码器在语义表示规模降低33.33%时实现22 dB的峰值信噪比（PSNR）；符号协议机将神经媒体访问控制（MAC）协议从4.55 MB压缩至1 KB（缩小99.98%）且性能无损失；联邦双向知识蒸馏在模型与数据异质性共存的情况下收敛，而FedAvg式平均方法表现不佳；知识图谱辅助概率图降低65%的传输能耗。本综述确定了基于TinyLM的6G语义通信的九大开放研究挑战，其中两项为文献中此前未明确提出的挑战。
英文摘要
Sixth-generation (6G) wireless networks are envisioned as AI-native systems in which semantic communication - transmitting task-relevant meaning rather than raw bits - moves beyond Shannon's classical bit-pipe model. Large language models (LLMs) dominate semantic encoding but are unsuitable for 6G user equipment and IoT devices, given prohibitive memory, energy, and latency costs. Tiny language models (TinyLMs) - compressed via TinyML techniques into kilobyte-to-megabyte memory and milliwatt power budgets - are the missing bridge between LLM-level semantic encoding and 6G edge hardware, yet no prior work systematically maps TinyML techniques onto semantic communication architectures for this purpose. This survey closes that gap through a two-axis taxonomy connecting six compression families (quantization, pruning, knowledge distillation, low-rank adaptation, neural architecture search, hybrid pipelines) to five semantic communication architectures (end-to-end joint source-channel coding, split learning, federated learning, knowledge-graph-assisted, and multi-task/cross-modal communication), synthesized with a quantitative meta-analysis of the model-size-versus-semantic-fidelity Pareto frontier. Representative results include a CNN-Transformer encoder achieving 22 dB PSNR at 33.33% semantic-representation size reduction; a symbolic protocol machine reducing a neural MAC protocol from 4.55 MB to 1 KB (99.98% smaller) with zero performance loss; federated bidirectional knowledge distillation converging under joint model-and-data heterogeneity where FedAvg-style averaging underperforms; and knowledge-graph-assisted probability graphs cutting transmission energy by 65%. The survey identifies nine open research challenges for TinyLM-enabled 6G semantic communication, including two not previously articulated in the literature.
发表机构
- IIT Dharwad（达瓦尔瓦德印度理工学院）
- Central University of Jammu, J&K（查谟中央大学）
- Manipal Institute of Technology（马尼拉理工学院）
机构由 AI 辅助整理，请以论文原文为准。
