mlsanityData to 14 Oct 2026

Spatiotemporal Forecasting Meets Efficiency: Causal Graph Process Neural Networks

arXiv 2405.18879 ↗First posted 29 May 2024cs.LGcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper 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

23 of 37 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  3. 2019Green AIcited by 627
  4. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  5. 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 413
  6. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 401
  7. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 275
  8. 2020DiffusionNet: Discretization Agnostic Learning on Surfacescited by 164
  9. 2019Stability Properties of Graph Neural Networkscited by 127
  10. 2021PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Modelscited by 118
  11. 2023LargeST: A Benchmark Dataset for Large-Scale Traffic Forecastingcited by 118
  12. 2020Deep Learning for Time Series Forecasting: Tutorial and Literature Surveycited by 117
11 more
  1. 2022On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networkscited by 64
  2. 2020A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecastingcited by 54
  3. 2022Scalable Spatiotemporal Graph Neural Networkscited by 52
  4. 2018GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Predictioncited by 47
  5. 2023Graph Signal Processing: History, Development, Impact, and Outlookcited by 39
  6. 2016Autoregressive Moving Average Graph Filteringcited by 35
  7. 2015Signal Processing on Graphs: Causal Modeling of Unstructured Datacited by 27
  8. 2018Forecasting Time Series with VARMA Recursions on Graphscited by 27
  9. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  10. 2022TIDE: Time Derivative Diffusion for Deep Learning on Graphscited by 17
  11. 2022Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecastingcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Role-Specific Predictive Geometries for Nonstationary Multivariate Graph-Signal Forecastingcited by 0