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 (34)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
• Graph Neural Network for Traffic Forecasting: A Survey
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
• Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• A Gentle Introduction to Deep Learning for Graphs
• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• Benchmarking Graph Neural Networks
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
• Graph Signal Processing: History, Development, Impact, and Outlook
• Differentiable Graph Module (DGM) for Graph Convolutional Networks
• Forecasting Time Series with VARMA Recursions on Graphs
• Understanding Pooling in Graph Neural Networks
• Monte Carlo Gradient Estimation in Machine Learning
• Representation Learning for Dynamic Graphs: A Survey
• Concept Drift and Anomaly Detection in Graph Streams
• Graphon Neural Networks and the Transferability of 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
• Gradient Estimation with Stochastic Softmax Tricks
• 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
• Graph State-Space Models and Latent Relational Inference
• Graph Kalman Filters
• Assessment of Spatio-Temporal Predictors in the Presence of Missing and Heterogeneous Data

Cited by in corpus (1)

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