Structure-Aware Multi-Hop Graph Convolution for Graph Neural Networks

TL;DR

This paper introduces a novel spatial graph convolution that incorporates structural information in feature space and multi-hop neighbor aggregation, enhancing node classification accuracy in GNNs for 3D point clouds and citation networks.

Contribution

It proposes two methods to improve graph convolution: using structural features in feature space and aggregating multi-hop neighbor information, integrated into GNNs.

Findings

Higher classification accuracy than existing methods

Effective multi-hop neighbor aggregation

Utilization of structural features improves performance

Abstract

In this paper, we propose a spatial graph convolution (GC) to classify signals on a graph. Existing GC methods are limited to using the structural information in the feature space. Additionally, the single step of GCs only uses features on the one-hop neighboring nodes from the target node. In this paper, we propose two methods to improve the performance of GCs: 1) Utilizing structural information in the feature space, and 2) exploiting the multi-hop information in one GC step. In the first method, we define three structural features in the feature space: feature angle, feature distance, and relational embedding. The second method aggregates the node-wise features of multi-hop neighbors in a GC. Both methods can be simultaneously used. We also propose graph neural networks (GNNs) integrating the proposed GC for classifying nodes in 3D point clouds and citation networks. In experiments, the proposed GNNs exhibited a higher classification accuracy than existing methods.