Fredformer：用于时间序列预测的频率去偏Transformer
Fredformer: Frequency Debiased Transformer for Time Series Forecasting
AI总结：
本文针对Transformer在时间序列预测中的频率偏差问题，提出Fredformer框架，通过跨频带均衡学习特征以缓解偏差，并引入轻量级注意力近似变体，在多个真实数据集上取得优于基线方法的性能。
摘要：
Transformer模型在时间序列预测中已展现出领先性能。然而，在一些复杂场景下，它倾向于学习数据中的低频特征而忽视高频特征，表现出频率偏差。这种偏差使模型无法准确捕获重要的高频数据特征。在本文中，我们进行了实证分析以理解这一偏差，并发现频率偏差源于模型不成比例地关注具有更高能量的频率特征。基于我们的分析，我们对这一偏差进行了形式化建模，并提出了Fredformer，一个基于Transformer的框架，旨在通过在不同频带上平等地学习特征来减轻频率偏差。该方法防止模型忽视对准确预测至关重要的较低幅度特征。大量实验表明了我们所提方法的有效性，该方法在不同的真实世界时间序列数据集上能够优于其他基线。此外，我们引入了Fredformer的一种轻量级变体，采用注意力矩阵近似，在参数更少、计算成本更低的情况下实现了可比的性能。代码可在以下地址获取：https://github.com/chenzRG/Fredformer
英文摘要：
The Transformer model has shown leading performance in time series forecasting. Nevertheless, in some complex scenarios, it tends to learn low-frequency features in the data and overlook high-frequency features, showing a frequency bias. This bias prevents the model from accurately capturing important high-frequency data features. In this paper, we undertook empirical analyses to understand this bias and discovered that frequency bias results from the model disproportionately focusing on frequency features with higher energy. Based on our analysis, we formulate this bias and propose Fredformer, a Transformer-based framework designed to mitigate frequency bias by learning features equally across different frequency bands. This approach prevents the model from overlooking lower amplitude features important for accurate forecasting. Extensive experiments show the effectiveness of our proposed approach, which can outperform other baselines in different real-world time-series datasets. Furthermore, we introduce a lightweight variant of the Fredformer with an attention matrix approximation, which achieves comparable performance but with much fewer parameters and lower computation costs. The code is available at: https://github.com/chenzRG/Fredformer
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
