Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures

TL;DR

LightTS introduces a lightweight,MLP-based architecture for multivariate time series forecasting that relies on two novel down-sampling strategies to preserve information. By combining continuous and interval sampling with Information Exchange Blocks, LightTS captures short-term local and long-term global patterns while efficiently exchanging information across series. Empirical results across eight datasets show LightTS achieves state-of-the-art or competitive performance on both short- and long-sequence tasks, with substantial FLOPS and runtime savings and improved robustness. The work demonstrates that simple MLP components, when paired with smart sampling and bottleneck interactions, can rival heavy architectures in efficiency and accuracy for real-world time series forecasting.

Abstract

Multivariate time series forecasting has seen widely ranging applications in various domains, including finance, traffic, energy, and healthcare. To capture the sophisticated temporal patterns, plenty of research studies designed complex neural network architectures based on many variants of RNNs, GNNs, and Transformers. However, complex models are often computationally expensive and thus face a severe challenge in training and inference efficiency when applied to large-scale real-world datasets. In this paper, we introduce LightTS, a light deep learning architecture merely based on simple MLP-based structures. The key idea of LightTS is to apply an MLP-based structure on top of two delicate down-sampling strategies, including interval sampling and continuous sampling, inspired by a crucial fact that down-sampling time series often preserves the majority of its information. We conduct extensive experiments on eight widely used benchmark datasets. Compared with the existing state-of-the-art methods, LightTS demonstrates better performance on five of them and comparable performance on the rest. Moreover, LightTS is highly efficient. It uses less than 5% FLOPS compared with previous SOTA methods on the largest benchmark dataset. In addition, LightTS is robust and has a much smaller variance in forecasting accuracy than previous SOTA methods in long sequence forecasting tasks.

Figures (5)

• Figure 1: The overview of LightTS. In Part I, the model captures the short/long-term dependencies and extract features of each time series. In Part II, the model learns the interdependencies among different time series and make predictions.
• Figure 2: The overview of IEBlock and the bottleneck design.
• Figure 3: Forecasting sequence randomly selected from ETTh1 (upper row) and Electricity (lower row). The shaded area is the range of forecasting results under five different random seeds for training.
• Figure 4: The ground truth (black) and the forecast (orange) for one variable in the Traffic dataset with the forecasting horizon of 24. The variable has daily patterns (short-term local patterns) and weekly patterns (long-range patterns). The green arrows point at daily patterns, where (a) and (b) which have continuous sampling are more accurate in forecasting than (c). The blue arrows point at weekly patterns, where (a) and (c) which have interval sampling are more accurate in forecasting than (b).
• Figure 5: The correlation between the interdependency modeled by LightTS and MTGNN. The improvement of channel projection for Solar and Electricity is significant in our ablation study, which suggests that the interdependencies among different variables are evident in these two datasets.