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。现有方法通常采用固定或单一长度的补丁对时间序列数据进行编码，然而这可能导致难以捕捉真实世界多周期时间序列中存在的复杂时间依赖关系。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Transformer编码层初始阶段，时间序列数据被编码为多个并行分支，每个分支利用检测到的周期特征进行处理，随后进入Transformer编码器模块。我们在长短期预测数据集上进行了广泛评估，将MultiResFormer与当前最优基线模型进行对比。实验表明，MultiResFormer在长期预测任务中优于基于补丁的Transformer基线模型，同时在参数量远小于CNN基线模型的情况下，仍能以较大优势持续超越后者。