提出新型线性注意力模型，高效处理长时序预测。
FRWKV:Frequency-Domain Linear Attention for Long-Term Time Series Forecasting
- 采用频域分析与线性注意力结合，计算复杂度降至O(T)。
- 在8个真实数据集上平均排名第一，性能显著提升。
- 适合需要高效建模长序列的工业级时序预测场景。
传统Transformer在长序列时间序列预测中因二次复杂度（O(T²)）和难以有效利用频域信息而面临瓶颈。受RWKV的O(T)线性注意力和频域建模启发，我们提出FRWKV，一种频域线性注意力框架，克服了上述限制。该模型将线性注意力机制与频域分析相结合，在注意力路径上实现O(T)计算复杂度的同时，利用频谱信息增强时序特征表示，支持可扩展的长序列建模。在八个真实世界数据集上，FRWKV实现平均排名第一。消融实验验证了线性注意力与频编码组件的关键作用。本工作展示了线性注意力与频域分析的强大协同效应，确立了可扩展时序建模的新范式。代码已开源：https://github.com/yangqingyuan-byte/FRWKV。
原文摘要 · Abstract (English)
Traditional Transformers face a major bottleneck in long-sequence time series forecasting due to their quadratic complexity $(\mathcal{O}(T^2))$ and their limited ability to effectively exploit frequency-domain information. Inspired by RWKV's $\mathcal{O}(T)$ linear attention and frequency-domain modeling, we propose FRWKV, a frequency-domain linear-attention framework that overcomes these limitations. Our model integrates linear attention mechanisms with frequency-domain analysis, achieving $\mathcal{O}(T)$ computational complexity in the attention path while exploiting spectral information to enhance temporal feature representations for scalable long-sequence modeling. Across eight real-world datasets, FRWKV achieves a first-place average rank. Our ablation studies confirm the critical roles of both the linear attention and frequency-encoder components. This work demonstrates the powerful synergy between linear attention and frequency analysis, establishing a new paradigm for scalable time series modeling. Code is available at this repository: https://github.com/yangqingyuan-byte/FRWKV.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。