Multivariate Time Series (MTS) forecasting involves modeling temporal
dependencies within historical records. Transformers have demonstrated
remarkable performance in MTS forecasting due to their capability to capture
long-term dependencies. However, prior work has been confined to modeling
temporal dependencies at either a fixed scale or multiple scales that
exponentially increase (most with base 2). This limitation hinders their
effectiveness in capturing diverse seasonalities, such as hourly and daily
patterns. In this paper, we introduce a dimension invariant embedding technique
that captures short-term temporal dependencies and projects MTS data into a
higher-dimensional space, while preserving the dimensions of time steps and
variables in MTS data. Furthermore, we present a novel Multi-scale Transformer
Pyramid Network (MTPNet), specifically designed to effectively capture temporal
dependencies at multiple unconstrained scales. The predictions are inferred
from multi-scale latent representations obtained from transformers at various
scales. Extensive experiments on nine benchmark datasets demonstrate that the
proposed MTPNet outperforms recent state-of-the-art methods.

使用多尺度 Transformer 的多变量时间序列预测中，引入了不变量嵌入技术用于捕捉短期时间依赖并将数据投射到高维空间，同时保留时间步和变量维度。进一步，提出了一种新颖的 Multi-scale Transformer 金字塔网络 (MTPNet), 用于有效地捕捉多个不受约束尺度上的时间依赖。在九个基准数据集上的广泛实验证明，提出的 MTPNet 优于最新的先进方法。