Graph Deep Learning for Time Series Forecasting

Abstract

Graph deep learning methods have become popular tools to process collections of correlated time series. Unlike traditional multivariate forecasting methods, graph-based predictors leverage pairwise relationships by conditioning forecasts on graphs spanning the time series collection. The conditioning takes the form of architectural inductive biases on the forecasting architecture, resulting in a family of models called spatiotemporal graph neural networks. These biases allow for training global forecasting models on large collections of time series while localizing predictions w.r.t. each element in the set (nodes) by accounting for correlations among them (edges). Recent advances in graph neural networks and deep learning for time series forecasting make the adoption of such processing framework appealing and timely. However, most studies focus on refining existing architectures by exploiting modern deep-learning practices. Conversely, foundational and methodological aspects have not been subject to systematic investigation. To fill this void, this tutorial paper aims to introduce a comprehensive methodological framework formalizing the forecasting problem and providing design principles for graph-based predictors, as well as methods to assess their performance. In addition, together with an overview of the field, we provide design guidelines and best practices, as well as an in-depth discussion of open challenges and future directions.

Published as a tutorial paper in ACM Computing Surveys

References in corpus (15)

• Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
• Graph Signal Processing: History, Development, Impact, and Outlook
• Understanding Pooling in Graph Neural Networks
• Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities
• Deep learning for dynamic graphs: models and benchmarks
• Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
• INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
• Temporal Graph Benchmark for Machine Learning on Temporal Graphs
• LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting
• Graph-based Multi-ODE Neural Networks for Spatio-Temporal Traffic Forecasting
• Sparse Graph Learning from Spatiotemporal Time Series
• Assessment of Spatio-Temporal Predictors in the Presence of Missing and Heterogeneous Data
• Graph Kalman Filters
• Graph State-Space Models and Latent Relational Inference

Cited by in corpus (1)

• Assessment of Spatio-Temporal Predictors in the Presence of Missing and Heterogeneous Data