Since graph learning could preserve the structure information of the samples to improve the learning ability, it has been widely applied in both shallow learning and deep learning. However, the current graph learning methods still suffer from the issues such as outlier influence and model robustness. In this paper, we propose a new dynamic graph neural network (DGCN) method to conduct semi-supervised classification on multi-view data by jointly conducting the graph learning and the classification task in a unified framework. Specifically, our method investigates three strategies to improve the quality of the graph before feeding it into the GCN model: (i) employing robust statistics to consider the sample importance for reducing the outlier influence, i.e. assigning every sample with soft weights so that the important samples are with large weights and outliers are with small or even zero weights; (ii) learning the common representation across all views to improve the quality of the graph for every view; and (iii) learning the complementary information from all initial graphs on multi-view data to further improve the learning of the graph for every view. As a result, each of the strategies could improve the robustness of the DGCN model. Moreover, they are complementary for reducing outlier influence from different aspects, i.e. the sample importance reduces the weights of the outliers, both the common representation and the complementary information improve the quality of the graph for every view. Experimental result on real data sets demonstrates the effectiveness of our method, compared to the comparison methods, in terms of multi-class classification performance.

中文翻译：

---

用于多视图数据分类的鲁棒和动态图卷积网络

由于图学习可以保留样本的结构信息以提高学习能力，因此在浅层学习和深度学习中都得到了广泛的应用。然而，目前的图学习方法仍然存在异常值影响和模型鲁棒性等问题。在本文中，我们提出了一种新的动态图神经网络（DGCN）方法，通过在一个统一的框架中联合进行图学习和分类任务来对多视图数据进行半监督分类。具体来说，我们的方法在将图输入 GCN 模型之前研究了三种提高图质量的策略：（i）采用稳健的统计数据来考虑样本重要性以减少异常值的影响，即 为每个样本分配软权重，使重要样本的权重较大，异常值的权重较小甚至为零；(ii) 学习所有视图的共同表示，以提高每个视图的图形质量；(iii) 从多视图数据上的所有初始图学习互补信息，以进一步改进每个视图的图学习。因此，每种策略都可以提高 DGCN 模型的鲁棒性。此外，它们对于减少来自不同方面的异常值影响是互补的，即样本重要性降低了异常值的权重，共同表示和互补信息都提高了每个视图的图形质量。真实数据集的实验结果证明了我们方法的有效性，