Generic Multimodal Spatially Graph Network for Spatially Embedded Network Representation Learning

TL;DR

This paper introduces GMu-SGCN, a novel multimodal graph convolutional network that effectively captures spatial features in embedded networks, significantly improving edge prediction accuracy in both natural and man-made networks.

Contribution

The paper presents a new GMu-SGCN model that incorporates multimodal spatial features for enhanced representation of spatially embedded networks, outperforming existing models.

Findings

Improves edge prediction accuracy by 37.1% over GraphSAGE.

Demonstrates effectiveness on both river and power networks.

Highlights importance of multidimensional spatial features.

Abstract

Spatially embedded networks (SENs) represent a special type of complex graph, whose topologies are constrained by the networks' embedded spatial environments. The graph representation of such networks is thereby influenced by the embedded spatial features of both nodes and edges. Accurate network representation of the graph structure and graph features is a fundamental task for various graph-related tasks. In this study, a Generic Multimodal Spatially Graph Convolutional Network (GMu-SGCN) is developed for efficient representation of spatially embedded networks. The developed GMu-SGCN model has the ability to learn the node connection pattern via multimodal node and edge features. In order to evaluate the developed model, a river network dataset and a power network dataset have been used as test beds. The river network represents the naturally developed SENs, whereas the power network represents a man-made network. Both types of networks are heavily constrained by the spatial environments and uncertainties from nature. Comprehensive evaluation analysis shows the developed GMu-SGCN can improve accuracy of the edge existence prediction task by 37.1\% compared to a GraphSAGE model which only considers the node's position feature in a power network test bed. Our model demonstrates the importance of considering the multidimensional spatial feature for spatially embedded network representation.