Portal de Periódicos da CAPES

Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning

2018; Association for the Advancement of Artificial Intelligence; Volume: 32; Issue: 1 Linguagem: Inglês

10.1609/aaai.v32i1.11604

2374-3468

Qimai Li, Zhichao Han, Xiao-Ming Wu,

Recommender Systems and Techniques

Many interesting problems in machine learning are being revisited with new deep learning tools. For graph-based semi-supervised learning, a recent important development is graph convolutional networks (GCNs), which nicely integrate local vertex features and graph topology in the convolutional layers. Although the GCN model compares favorably with other state-of-the-art methods, its mechanisms are not clear and it still requires considerable amount of labeled data for validation and model selection. In this paper, we develop deeper insights into the GCN model and address its fundamental limits. First, we show that the graph convolution of the GCN model is actually a special form of Laplacian smoothing, which is the key reason why GCNs work, but it also brings potential concerns of over-smoothing with many convolutional layers. Second, to overcome the limits of the GCN model with shallow architectures, we propose both co-training and self-training approaches to train GCNs. Our approaches significantly improve GCNs in learning with very few labels, and exempt them from requiring additional labels for validation. Extensive experiments on benchmarks have verified our theory and proposals.