# Spatial Graph Convolutional Networks

arXiv: https://arxiv.org/abs/1909.05310 · HTML: https://mlsanity.com/paper/1909.05310/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2019.

## Built on by (most cited first, 4 of 4)

- [Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA) for Remote Land-use Change Detection](https://mlsanity.com/paper/2303.14322/) (2023)
- [Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation](https://mlsanity.com/paper/2104.11176/) (2021)
- [Distance-Geometric Graph Attention Network (DG-GAT) for 3D Molecular Geometry](https://mlsanity.com/paper/2207.08023/) (2022)
- [CellTypeGraph: A New Geometric Computer Vision Benchmark](https://mlsanity.com/paper/2205.08166/) (2022)

## Abstract (arXiv)

Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compounds. However, GCNs lack the ability to take into account the ordering of node neighbors, even when there is a geometric interpretation of the graph vertices that provides an order based on their spatial positions. To remedy this issue, we propose Spatial Graph Convolutional Network (SGCN) which uses spatial features to efficiently learn from graphs that can be naturally located in space. Our contribution is threefold: we propose a GCN-inspired architecture which (i) leverages node positions, (ii) is a proper generalization of both GCNs and Convolutional Neural Networks (CNNs), (iii) benefits from augmentation which further improves the performance and assures invariance with respect to the desired properties. Empirically, SGCN outperforms state-of-the-art graph-based methods on image classification and chemical tasks.