Positional Encoder Graph Neural Networks for Geographic Data

Abstract

Graph neural networks (GNNs) provide a powerful and scalable solution for modeling continuous spatial data. However, they often rely on Euclidean distances to construct the input graphs. This assumption can be improbable in many real-world settings, where the spatial structure is more complex and explicitly non-Euclidean (e.g., road networks). Here, we propose PE-GNN, a new framework that incorporates spatial context and correlation explicitly into the models. Building on recent advances in geospatial auxiliary task learning and semantic spatial embeddings, our proposed method (1) learns a context-aware vector encoding of the geographic coordinates and (2) predicts spatial autocorrelation in the data in parallel with the main task. On spatial interpolation and regression tasks, we show the effectiveness of our approach, improving performance over different state-of-the-art GNN approaches. We observe that our approach not only vastly improves over the GNN baselines, but can match Gaussian processes, the most commonly utilized method for spatial interpolation problems.

AISTATS 2023

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Semi-Supervised Classification with Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• Kriging Convolutional Networks
• Augmenting correlation structures in spatial data using deep generative models
• Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells
• Structured Variational Inference in Continuous Cox Process Models