Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting

Zezhi Shao, Zhao Zhang, Fei Wang, Wei Wei, Yongjun Xu

2022-08-10Traffic Prediction Time Series Forecasting Time Series Multivariate Time Series Forecasting Time Series Analysis

Paper PDF Code(official)Code

Abstract

Multivariate Time Series (MTS) forecasting plays a vital role in a wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS forecasting methods due to their state-of-the-art performance. However, recent works are becoming more sophisticated with limited performance improvements. This phenomenon motivates us to explore the critical factors of MTS forecasting and design a model that is as powerful as STGNNs, but more concise and efficient. In this paper, we identify the indistinguishability of samples in both spatial and temporal dimensions as a key bottleneck, and propose a simple yet effective baseline for MTS forecasting by attaching Spatial and Temporal IDentity information (STID), which achieves the best performance and efficiency simultaneously based on simple Multi-Layer Perceptrons (MLPs). These results suggest that we can design efficient and effective models as long as they solve the indistinguishability of samples, without being limited to STGNNs.

Results

Task	Dataset	Metric	Value	Model
Traffic Prediction	LargeST	CA MAE	18.41	STID
Traffic Prediction	LargeST	GBA MAE	20.22	STID
Traffic Prediction	LargeST	GLA MAE	19.76	STID
Traffic Prediction	LargeST	SD MAE	17.86	STID

Related Papers

The Power of Architecture: Deep Dive into Transformer Architectures for Long-Term Time Series Forecasting2025-07-17 MoTM: Towards a Foundation Model for Time Series Imputation based on Continuous Modeling2025-07-17 Emergence of Functionally Differentiated Structures via Mutual Information Optimization in Recurrent Neural Networks2025-07-17 Data Augmentation in Time Series Forecasting through Inverted Framework2025-07-15 D3FL: Data Distribution and Detrending for Robust Federated Learning in Non-linear Time-series Data2025-07-15 Federated Learning with Graph-Based Aggregation for Traffic Forecasting2025-07-13 Towards Interpretable Time Series Foundation Models2025-07-10 MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models2025-07-09