Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting

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. STGNNs jointly model the spatial and temporal patterns of MTS through graph neural networks and sequential models, significantly improving the prediction accuracy. But limited by model complexity, most STGNNs only consider short-term historical MTS data, such as data over the past one hour. However, the patterns of time series and the dependencies between them (i.e., the temporal and spatial patterns) need to be analyzed based on long-term historical MTS data. To address this issue, we propose a novel framework, in which STGNN is Enhanced by a scalable time series Pre-training model (STEP). Specifically, we design a pre-training model to efficiently learn temporal patterns from very long-term history time series (e.g., the past two weeks) and generate segment-level representations. These representations provide contextual information for short-term time series input to STGNNs and facilitate modeling dependencies between time series. Experiments on three public real-world datasets demonstrate that our framework is capable of significantly enhancing downstream STGNNs, and our pre-training model aptly captures temporal patterns.

Accepted by SIGKDD 2022 (Research Track)

References in corpus (5)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Sequence to Sequence Learning with Neural Networks
• Pre-trained Models for Natural Language Processing: A Survey
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

Cited by in corpus (11)

• Foundation Models for Time Series Analysis: A Tutorial and Survey
• Deep Learning for Time Series Forecasting: A Survey
• LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
• UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction
• Generative Pretrained Hierarchical Transformer for Time Series Forecasting
• Scalable Transformer for High Dimensional Multivariate Time Series Forecasting
• OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction
• A Data-driven Region Generation Framework for Spatiotemporal Transportation Service Management
• A Co-training Approach for Noisy Time Series Learning
• Nearest Neighbor Multivariate Time Series Forecasting
• Enhancing Spatiotemporal Traffic Prediction through Urban Human Activity Analysis