FM-LLM：一种用于适配大语言模型（LLMs）进行时间序列预测的频率增强型混合专家框架
FM-LLM: A frequency-enhanced mixture-of-experts framework for adapting LLMs to time series forecasting
- Beijing University of Posts and Telecommunications（北京邮电大学）
- China Telecom Research Institute（中国电信研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出FM-LLM框架，通过频谱标记对齐器与非对称MoE解码器等设计，在11个基准的多数指标上优于现有LLM基线，且具备良好迁移性。
AI中文摘要：
大语言模型（LLMs）的最新进展推动了时间序列预测的跨模态解决方案。然而，现有方法严重依赖文本提示进行模态对齐，带来了显著的计算开销，且未能利用时间序列数据中固有的丰富频谱动态。为实现对冻结LLMs的无提示、频率感知适配，我们提出FM-LLM（Frequency-Enhanced Mixture-of-Experts for adapting LLMs to Time Series Forecasting，频率增强型混合专家时间序列预测适配大语言模型框架），这是一种基于约束非对称耦合的自回归框架。基于傅里叶分析网络（FAN）的频谱标记对齐器以数值兼容性将结构化谐波表示直接注入冻结的LLMs。非对称混合专家（MoE）解码器实现角色分离：带有轻量FAN层的共享专家重构全局周期主干，而受限于标准前馈网络（FFNs）的路由专家则专门用于建模非周期残差动态。时频混合损失函数联合优化时间精度与频谱一致性，缓解长 horizon 自回归滚动过程中的误差累积。在11个公开基准上评估，FM-LLM在78项评估指标中的59项达到了最优性能。与最强的基于LLMs的自回归基线相比，它在均方误差（MSE）上平均提升5.3%，在平均绝对误差（MAE）上平均提升5.6%，MSE的最大提升达8.0%，MAE的最大提升达8.4%。FM-LLM还展现出稳健的可迁移性，在10%少样本和零样本预测场景中保持了优异性能。
英文摘要：
Recent advances in Large Language Models (LLMs) have spurred cross-modal solutions for time-series forecasting. However, existing methods rely heavily on textual prompts for modality alignment-introducing nontrivial computational overhead and failing to leverage the rich spectral dynamics inherent in time-series data. To enable prompt-free, frequency-aware adaptation of frozen LLMs, we propose FM-LLM (Frequency-Enhanced Mixture-of-Experts for adapting LLMs to Time Series Forecasting), an autoregressive framework grounded in constrained asymmetric coupling. A Fourier Analysis Network (FAN)-based spectral token aligner injects structured harmonic representations directly into the frozen LLM with numerical compatibility. An asymmetric Mixture-of-Experts (MoE) decoder enforces role separation: shared experts with lightweight FAN layers reconstruct the global periodic backbone, while routed experts-restricted to standard FFNs-specialize in modeling non-periodic residual dynamics. A time-frequency hybrid loss function jointly optimizes temporal accuracy and spectral consistency, mitigating error accumulation during long-horizon autoregressive rollouts. Evaluated across eleven public benchmarks, FM-LLM achieves state-of-the-art performance on 59 out of 78 evaluation metrics. Compared to the strongest autoregressive LLM-based baseline, it delivers average improvements of 5.3% in MSE and 5.6% in MAE, with maximum gains reaching 8.0% for MSE and 8.4% for MAE. FM-LLM also demonstrates robust transferability, maintaining superior performance in 10% few-shot and zero-shot forecasting scenarios.
