Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks

TL;DR

This paper introduces a method for jointly learning graph structures and node features in Graph Convolutional Neural Networks, enhancing adaptability and performance across various graph data applications.

Contribution

It proposes a dynamic graph learning approach using Mahalanobis distance metric learning, optimizing graph structures layer-wise for improved accuracy and robustness.

Findings

Outperforms existing methods on point cloud and citation datasets.

Improves accuracy and robustness of GCNNs.

Efficient low-dimensional optimization for graph learning.

Abstract

Graph Convolutional Neural Networks (GCNNs) extend classical CNNs to graph data domain, such as brain networks, social networks and 3D point clouds. It is critical to identify an appropriate graph for the subsequent graph convolution. Existing methods manually construct or learn one fixed graph for all the layers of a GCNN. In order to adapt to the underlying structure of node features in different layers, we propose dynamic learning of graphs and node features jointly in GCNNs. In particular, we cast the graph optimization problem as distance metric learning to capture pairwise similarities of features in each layer. We deploy the Mahalanobis distance metric and further decompose the metric matrix into a low-dimensional matrix, which converts graph learning to the optimization of a low-dimensional matrix for efficient implementation. Extensive experiments on point clouds and citation network datasets demonstrate the superiority of the proposed method in terms of both accuracies and robustness.