# Spatiotemporal Forecasting Meets Efficiency: Causal Graph Process Neural Networks

arXiv: https://arxiv.org/abs/2405.18879 · HTML: https://mlsanity.com/paper/2405.18879/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 23 of 23)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [Graph Signal Processing: Overview, Challenges and Applications](https://mlsanity.com/paper/1712.00468/) (2017)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [Structured Sequence Modeling with Graph Convolutional Recurrent Networks](https://mlsanity.com/paper/1612.07659/) (2016)
- [DiffusionNet: Discretization Agnostic Learning on Surfaces](https://mlsanity.com/paper/2012.00888/) (2020)
- [Stability Properties of Graph Neural Networks](https://mlsanity.com/paper/1905.04497/) (2019)
- [PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models](https://mlsanity.com/paper/2104.07788/) (2021)
- [LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting](https://mlsanity.com/paper/2306.08259/) (2023)
- [Deep Learning for Time Series Forecasting: Tutorial and Literature Survey](https://mlsanity.com/paper/2004.10240/) (2020)
- [On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networks](https://mlsanity.com/paper/2212.02374/) (2022)
- [A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting](https://mlsanity.com/paper/2006.11583/) (2020)
- [Scalable Spatiotemporal Graph Neural Networks](https://mlsanity.com/paper/2209.06520/) (2022)
- [GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction](https://mlsanity.com/paper/1812.04206/) (2018)
- [Graph Signal Processing: History, Development, Impact, and Outlook](https://mlsanity.com/paper/2303.12211/) (2023)
- [Autoregressive Moving Average Graph Filtering](https://mlsanity.com/paper/1602.04436/) (2016)
- [Signal Processing on Graphs: Causal Modeling of Unstructured Data](https://mlsanity.com/paper/1503.00173/) (2015)
- [Forecasting Time Series with VARMA Recursions on Graphs](https://mlsanity.com/paper/1810.08581/) (2018)
- [Graph Deep Learning for Time Series Forecasting](https://mlsanity.com/paper/2310.15978/) (2023)
- [TIDE: Time Derivative Diffusion for Deep Learning on Graphs](https://mlsanity.com/paper/2212.02483/) (2022)
- [Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting](https://mlsanity.com/paper/2205.08689/) (2022)

## Built on by (most cited first, 1 of 1)

- [Role-Specific Predictive Geometries for Nonstationary Multivariate Graph-Signal Forecasting](https://mlsanity.com/paper/2609.06519/) (2026)

## Abstract (arXiv)

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.