Multipath Graph Convolutional Neural Networks
This work addresses performance issues in graph neural networks for node property prediction, offering an incremental improvement over existing methods.
The authors tackled the problem of vanishing gradients, over-fitting, and over-smoothing in deep graph convolutional networks by proposing a Multipath Graph Convolutional Neural Network that aggregates outputs from multiple shallow networks, resulting in increased test accuracy and faster convergence with fewer training epochs on benchmark datasets.
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