Perturbations targeting the graph structure have proven to be extremely effective in reducing the performance of Graph Neural Networks (GNNs), and traditional defenses such as adversarial training do not seem to be able to improve robustness. This work is motivated by the observation that adversarially injected edges effectively can be viewed as additional samples to a node's neighborhood aggregation function, which results in distorted aggregations accumulating over the layers. Conventional GNN aggregation functions, such as a sum or mean, can be distorted arbitrarily by a single outlier. We propose a robust aggregation function motivated by the field of robust statistics. Our approach exhibits the largest possible breakdown point of 0.5, which means that the bias of the aggregation is bounded as long as the fraction of adversarial edges of a node is less than 50\%. Our novel aggregation function, Soft Medoid, is a fully differentiable generalization of the Medoid and therefore lends itself well for end-to-end deep learning. Equipping a GNN with our aggregation improves the robustness with respect to structure perturbations on Cora ML by a factor of 3 (and 5.5 on Citeseer) and by a factor of 8 for low-degree nodes.
翻译:针对图形结构的扰动已证明在降低图形神经网络(GNNs)的性能方面极为有效,而传统防御,例如对抗性训练似乎无法提高稳健性。这项工作的动机是,观察到对称注射的边缘实际上可被视为节点周围集合功能的额外样本,从而导致在层层上积累扭曲的集合。常规GNN集合功能,例如总和或中值,可以被一个单一的外端任意扭曲。我们提议了一个由可靠统计领域驱动的强健的聚合功能。我们的方法显示0.5的最小分解点,这意味着只要节点的对称边缘部分小于50 ⁇,集合的偏差就会被捆绑住。我们的新颖的组合功能Soft Meduid是完全不同的组合功能,因此可以很好地进行端到端深的学习。用我们的总合来配置的GNNN,可以提高科拉 ML结构的坚固度。我们的方法显示了0.5的分解点,也就是说,只要节点的对准度小节点的边缘部分小于50 ⁇ 。我们的新组合功能,Soft Medule 是一个完全的概观,通过低度的8.5摄氏8系数和低度系数可以提高科拉ML结构的坚固度。