Real-world time-series datasets are often multivariate with complex dynamics. To capture this complexity, high capacity architectures like recurrent- or attention-based sequential deep learning models have become popular. However, recent work demonstrates that simple univariate linear models can outperform such deep learning models on several commonly used academic benchmarks. Extending them, in this paper, we investigate the capabilities of linear models for time-series forecasting and present Time-Series Mixer (TSMixer), a novel architecture designed by stacking multi-layer perceptrons (MLPs). TSMixer is based on mixing operations along both the time and feature dimensions to extract information efficiently. On popular academic benchmarks, the simple-to-implement TSMixer is comparable to specialized state-of-the-art models that leverage the inductive biases of specific benchmarks. On the challenging and large scale M5 benchmark, a real-world retail dataset, TSMixer demonstrates superior performance compared to the state-of-the-art alternatives. Our results underline the importance of efficiently utilizing cross-variate and auxiliary information for improving the performance of time series forecasting. We present various analyses to shed light into the capabilities of TSMixer. The design paradigms utilized in TSMixer are expected to open new horizons for deep learning-based time series forecasting. The implementation is available at https://github.com/google-research/google-research/tree/master/tsmixer

翻译：真实世界的时间序列数据集通常是多元的，且具有复杂动态特性。为捕捉这种复杂性，基于循环或注意力机制的序列深度学习模型等高容量架构逐渐流行。然而，近期研究表明，简单的单变量线性模型能在多个常用学术基准上超越此类深度学习模型。在此基础上，本文进一步探究线性模型在时间序列预测中的能力，并提出时间序列混合器（TSMixer）——一种通过堆叠多层感知机（MLP）设计的新型架构。TSMixer基于沿时间维度和特征维度的混合操作，以高效提取信息。在主流学术基准上，易于实现的TSMixer性能可媲美利用特定基准归纳偏置的专业化先进模型。在具有挑战性的大规模M5基准（一个真实零售数据集）上，TSMixer展现出优于先进替代模型的性能。我们的结果强调了高效利用跨变量信息和辅助信息对于提升时间序列预测性能的重要性。我们通过多种分析揭示TSMixer的能力。TSMixer采用的设计范式有望为基于深度学习的时间序列预测开辟新方向。实现代码详见https://github.com/google-research/google-research/tree/master/tsmixer