The effectiveness of Graph Convolutional Networks (GCNs) has been demonstrated in a wide range of graph-based machine learning tasks. However, the update of parameters in GCNs is only from labeled nodes, lacking the utilization of unlabeled data. In this paper, we apply Virtual Adversarial Training (VAT), an adversarial regularization method based on both labeled and unlabeled data, on the supervised loss of GCN to enhance its generalization performance. By imposing virtually adversarial smoothness on the posterior distribution in semi-supervised learning, VAT yields improvement on the Symmetrical Laplacian Smoothness of GCNs. In addition, due to the difference of property in features, we perturb virtual adversarial perturbations on sparse and dense features, resulting in GCN Sparse VAT (GCNSVAT) and GCN Dense VAT (GCNDVAT) algorithms, respectively. Extensive experiments verify the effectiveness of our two methods across different training sizes. Our work paves the way towards better understanding the direction of improvement on GCNs in the future.
翻译:在一系列基于图形的机器学习任务中,图表革命网络(GCN)的实效得到了证明,然而,GCN参数的更新仅来自标签的节点,没有使用未贴标签的数据;在本文中,我们采用了虚拟反向培训(VAT),这是一种基于标签的和未贴标签的数据的对抗性规范化方法,其基础是监督地丢失GCN,以提高其一般性能。通过在半监督的学习中,对后方分布几乎是对抗性的平稳,增值税提高了GCN的对称性拉平板滑度。此外,由于地物特性不同,我们对稀薄和稠密的地物进行了虚拟对抗性侵扰,分别产生了GCN sparse VAT(GCNSVAT)和GCN Dense VAT(GCNDVAT)的算法。广泛的实验验证了我们两种方法在不同培训规模上的有效性。我们的工作为更好地理解未来GCN改进方向铺平了道路。