用于CSI反馈的学习件：特定场景的小型模型可发挥大作用
Learnware for CSI Feedback: Scene-specific Small Models Can Do Big
浏览论文内容
中文总结 AI 辅助
针对6G CSI反馈的模型泛化与场景性能权衡问题，提出基于学习件的模型仓库框架，可高效检索匹配的预训练模型，在LOS/NLOS场景下性能优于通用模型，减少训练开销并增强隐私。
中文摘要 AI 辅助
智能信道状态信息（CSI）反馈对实现未来6G系统的高容量和频谱效率目标至关重要，但现有的深度学习解决方案在模型泛化能力和特定场景性能之间存在权衡。大型神经网络泛化能力强，但会带来高计算和调优成本；而小型模型在特定环境中表现出色，但需要为每个基站（BS）重复进行高成本的端到端训练。为应对这些挑战，我们提出一种基于模型仓库的部署框架，其中中央AI数据中心维护特定场景CSI模型的目录。该仓库由基于学习件（Learnware）的框架增强，每个模型都关联一个规范，包括语义部分（网络架构参数）和统计部分（码本指纹嵌入训练数据分布）。基站仅提交其本地统计规范，即可检索最相关的预训练模型，通过避免原始CSI传输增强数据隐私，并大幅降低检索延迟和通信开销。我们进一步开发了一种数据驱动的搜索策略，将码本指纹与模型性能匹配，实现超过90%的选择准确率。在仿真中，我们的方案在视距（LOS）和非视距（NLOS）场景下，分别比通用模型实现了18.8%和57.7%的性能提升，同时将本地微调所需的样本量减少多达1000个、轮次减少多达100个epoch。这种基于学习件的方法最大限度减少了冗余训练，最大化了模型复用，并支持CSI反馈模型的快速、增强隐私的部署。
英文摘要
Intelligent channel state information (CSI) feedback is essential for realizing the high capacity and spectral efficiency goals of future 6G systems, yet existing deep learning solutions face a trade-off between model generalization and scenario-specific performance. Large neural networks generalize well but incur high computational and tuning costs, while small models excel in particular environments but require repetitive costly end-to-end training for each base station (BS). To address these challenges, we introduce a model repository-based deployment framework in which a centralized AI data center maintains a catalog of scene-specific CSI models. The repository is enhanced with a Learnware-based framework, where each model is associated with a specification including semantic part (network architecture parameters) and statistical part (codeboo-fingerprint embeddings of training-data distributions). A BS submits only its local statistical specifications to retrieve the most relevant pre-trained model, enhancing data privacy by avoiding raw CSI transmission and drastically reducing retrieval latency and communication overhead. We further develop a data-driven search strategy that matches codebook fingerprints to model performance, achieving over 90% selection accuracy. In simulations, our scheme yields 18.8% and 57.7% performance improvements over the General Model in LOS and NLOS scenarios, respectively while reducing local fine-tuning by up to 1000 samples and 100 epochs. This Learnware-based approach minimizes redundant training, maximizes model reuse, and supports rapid,privacy-enhancing deployment of CSI feedback models.
发表机构
- Southeast University（东南大学）
- The Hong Kong University of Science and Technology（香港科技大学）
- National Sun Yat-sen University（国立中山大学）
- Nanjing University（南京大学）
机构由 AI 辅助整理，请以论文原文为准。
