提出频谱偏差增强方法，提升时序模型长期预测能力。
FreIE: Low-Frequency Spectral Bias in Neural Networks for Time-Series Tasks
- 通过频域正则化显式抑制低频偏差
- 在主流模型上验证频谱偏差普遍存在
- 可直接嵌入模型的即插即用损失函数
时间序列固有的自相关性给多变量时序预测带来持续挑战。近年来，将频域信息融入模型以辅助长期预测已成为广泛采用的方法。许多研究者独立观察到神经网络存在频谱偏差现象，即模型优先拟合低频信号而非高频信号。然而，这一现象常被归因于特定架构设计，而非普遍特性。为统一理解长期时序预测中的频谱偏差，我们对现有主流模型进行了大量实证实验，结果表明几乎所有模型均表现出该现象。为此，我们提出FreLE（Frequency Loss Enhancement）算法，通过显式与隐式频域正则化增强模型泛化能力。该方法为即插即用型损失函数单元，大量实验验证其优越性能。代码已开源：https://github.com/Chenxing-Xuan/FreLE。
原文摘要 · Abstract (English)
The inherent autocorrelation of time series data presents an ongoing challenge to multivariate time series prediction. Recently, a widely adopted approach has been the incorporation of frequency domain information to assist in long-term prediction tasks. Many researchers have independently observed the spectral bias phenomenon in neural networks, where models tend to fit low-frequency signals before high-frequency ones. However, these observations have often been attributed to the specific architectures designed by the researchers, rather than recognizing the phenomenon as a universal characteristic across models. To unify the understanding of the spectral bias phenomenon in long-term time series prediction, we conducted extensive empirical experiments to measure spectral bias in existing mainstream models. Our findings reveal that virtually all models exhibit this phenomenon. To mitigate the impact of spectral bias, we propose the FreLE (Frequency Loss Enhancement) algorithm, which enhances model generalization through both explicit and implicit frequency regularization. This is a plug-and-play model loss function unit. A large number of experiments have proven the superior performance of FreLE. Code is available at https://github.com/Chenxing-Xuan/FreLE.
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。