Multipath Graph Convolutional Neural Networks

TL;DR

This paper introduces a novel multipath graph convolutional neural network that combines outputs from multiple shallow networks, improving accuracy and convergence speed in node property prediction tasks.

Contribution

The paper proposes a new multipath GCN architecture that aggregates multiple shallow networks to enhance expressive power and training efficiency.

Findings

Achieves higher test accuracy on benchmark datasets.

Requires fewer epochs to converge compared to traditional deep GCNs.

Reduces issues like vanishing gradients and over-smoothing.

Abstract

Graph convolution networks have recently garnered a lot of attention for representation learning on non-Euclidean feature spaces. Recent research has focused on stacking multiple layers like in convolutional neural networks for the increased expressive power of graph convolution networks. However, simply stacking multiple graph convolution layers lead to issues like vanishing gradient, over-fitting and over-smoothing. Such problems are much less when using shallower networks, even though the shallow networks have lower expressive power. In this work, we propose a novel Multipath Graph convolutional neural network that aggregates the output of multiple different shallow networks. We train and test our model on various benchmarks datasets for the task of node property prediction. Results show that the proposed method not only attains increased test accuracy but also requires fewer training epochs to converge. The full implementation is available at https://github.com/rangan2510/MultiPathGCN