Graph neural networks are a popular variant of neural networks that work with graph-structured data. In this work, we consider combining graph neural networks with the energy-based view of Grathwohl et al. (2019) with the aim of obtaining a more robust classifier. We successfully implement this framework by proposing a novel method to ensure generation over features as well as the adjacency matrix and evaluate our method against the standard graph convolutional network (GCN) architecture (Kipf & Welling (2016)). Our approach obtains comparable discriminative performance while improving robustness, opening promising new directions for future research for energy-based graph neural networks.
翻译:在这项工作中,我们考虑将图形神经网络与Grathwohl等人(2019年)的基于能源的观点结合起来,以便获得一个更强有力的分类器。我们成功地实施了这一框架,提出了一种新颖的方法,以确保生成超特性和相邻矩阵,并对照标准图形革命网络架构(Kipf & Welling (2016年))评估我们的方法。我们的方法在提高稳健性的同时取得了相似的歧视性性能,为未来基于能源的图形神经网络的研究开辟了有希望的新方向。