提出点级归一化方法，解决时间序列内部分布漂移问题。
Inner-Instance Normalization for Time Series Forecasting
- 设计两种点级归一化方法，捕捉时间序列内部动态变化。
- 在多个基准上验证，显著提升模型预测精度。
- 适合处理非平稳时间序列的场景，如金融与气象预测。
真实世界的时间序列受多种因素影响，表现出复杂的非平稳特性。非平稳性会导致分布漂移，即时间序列的统计特性随时间变化，从而负面影响模型性能。尽管已有若干实例归一化技术用于缓解时间序列中的分布漂移问题，但现有方法未能考虑单个实例内部的分布变化，导致性能受限。为应对实例内部的分布漂移，我们提出两种新型点级方法：学习分布（LD）和学习条件分布（LCD）。LD通过在不同时间步使用不同参数拟合输入与输出的内部分布，消除内部差异；LCD则利用神经网络预测输出的缩放系数。我们在多个公开基准上，结合不同主干模型评估了这两种方法的性能，并通过对比实验验证了点级范式的有效性。
原文摘要 · Abstract (English)
Real-world time series are influenced by numerous factors and exhibit complex non-stationary characteristics. Non-stationarity can lead to distribution shifts, where the statistical properties of time series change over time, negatively impacting model performance. Several instance normalization techniques have been proposed to address distribution shifts in time series forecasting. However, existing methods fail to account for shifts within individual instances, leading to suboptimal performance. To tackle inner-instance distribution shifts, we propose two novel point-level methods: Learning Distribution (LD) and Learning Conditional Distribution (LCD). LD eliminates internal discrepancies by fitting the internal distribution of input and output with different parameters at different time steps, while LCD utilizes neural networks to predict scaling coefficients of the output. We evaluate the performance of the two methods with various backbone models across public benchmarks and demonstrate the effectiveness of the point-level paradigm through comparative experiments.
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。