Spatiotemporal Forecasting Meets Efficiency: Causal Graph Process Neural Networks

TL;DR

This paper introduces CGProNet, a novel neural network combining Causal Graph Processes and GNNs for efficient, scalable, and accurate spatiotemporal forecasting, reducing computational resources while maintaining performance.

Contribution

It proposes CGProNet, a non-linear model that uses higher-order graph filters to improve efficiency and scalability in spatiotemporal forecasting tasks.

Findings

CGProNet reduces memory and runtime compared to traditional methods.

Theoretical stability analysis supports CGProNet's robustness.

Experimental results show competitive forecasting accuracy.

Abstract

Graph Neural Networks (GNNs) have advanced spatiotemporal forecasting by leveraging relational inductive biases among sensors (or any other measuring scheme) represented as nodes in a graph. However, current methods often rely on Recurrent Neural Networks (RNNs), leading to increased runtimes and memory use. Moreover, these methods typically operate within 1-hop neighborhoods, exacerbating the reduction of the receptive field. Causal Graph Processes (CGPs) offer an alternative, using graph filters instead of MLP layers to reduce parameters and minimize memory consumption. This paper introduces the Causal Graph Process Neural Network (CGProNet), a non-linear model combining CGPs and GNNs for spatiotemporal forecasting. CGProNet employs higher-order graph filters, optimizing the model with fewer parameters, reducing memory usage, and improving runtime efficiency. We present a comprehensive theoretical and experimental stability analysis, highlighting key aspects of CGProNet. Experiments on synthetic and real data demonstrate CGProNet's superior efficiency, minimizing memory and time requirements while maintaining competitive forecasting performance.