Transformer-based models have greatly pushed the boundaries of time series forecasting recently. Existing methods typically encode time series data into $\textit{patches}$ using one or a fixed set of patch lengths. This, however, could result in a lack of ability to capture the variety of intricate temporal dependencies present in real-world multi-periodic time series. In this paper, we propose MultiResFormer, which dynamically models temporal variations by adaptively choosing optimal patch lengths. Concretely, at the beginning of each layer, time series data is encoded into several parallel branches, each using a detected periodicity, before going through the transformer encoder block. We conduct extensive evaluations on long- and short-term forecasting datasets comparing MultiResFormer with state-of-the-art baselines. MultiResFormer outperforms patch-based Transformer baselines on long-term forecasting tasks and also consistently outperforms CNN baselines by a large margin, while using much fewer parameters than these baselines.

翻译：基于Transformer的模型近年来极大地推动了时间序列预测领域的发展。现有方法通常采用单一或固定的一组补丁长度将时间序列数据编码为$\textit{补丁}$。然而，这种做法可能导致模型无法捕捉真实世界中多周期时间序列所蕴含的复杂时间依赖关系多样性。本文提出MultiResFormer模型，通过自适应选择最优补丁长度来动态建模时间变化。具体而言，在每个层的起始阶段，时间序列数据被编码为多个并行分支，每个分支采用检测到的周期模式，随后再进入Transformer编码块。我们在长时和短时预测数据集上进行了广泛评估，将MultiResFormer与最先进的基线模型进行比较。结果表明，MultiResFormer在长时预测任务中优于基于补丁的Transformer基线模型，同时以远少于这些基线模型的参数量，持续大幅超越CNN基线模型。