Graph Learning-Convolutional Networks
This addresses a bottleneck in graph-based semi-supervised learning for researchers and practitioners by integrating graph learning and convolution, though it is incremental as it builds on existing graph CNN frameworks.
The paper tackles the problem of suboptimal fixed graph structures in graph CNNs for semi-supervised learning by proposing a Graph Learning-Convolutional Network (GLCN) that learns an optimal graph structure, resulting in significant performance improvements over state-of-the-art methods on seven benchmarks.
Recently, graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks. However, existing graph CNNs generally use a fixed graph which may be not optimal for semi-supervised learning tasks. In this paper, we propose a novel Graph Learning-Convolutional Network (GLCN) for graph data representation and semi-supervised learning. The aim of GLCN is to learn an optimal graph structure that best serves graph CNNs for semi-supervised learning by integrating both graph learning and graph convolution together in a unified network architecture. The main advantage is that in GLCN, both given labels and the estimated labels are incorporated and thus can provide useful 'weakly' supervised information to refine (or learn) the graph construction and also to facilitate the graph convolution operation in GLCN for unknown label estimation. Experimental results on seven benchmarks demonstrate that GLCN significantly outperforms state-of-the-art traditional fixed structure based graph CNNs.