论文标题
防御图形卷积网络通过贝叶斯自我诉讼来防止动态图扰动
Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision
论文作者
论文摘要
近年来，大量证据表明，图形卷积网络（GCN）在节点分类任务上取得了非凡的成就。但是，GCN可能容易受到对标签筛选动态图的对抗性攻击的影响。许多现有的作品旨在增强GCN的鲁棒性。例如，对抗性训练用于保护GCN免受恶意扰动。但是，这些作品在动态图上失败了，标签稀缺是一个紧迫的问题。为了克服标签稀缺性，自我训练的尝试将伪标记分配给高度自信的未标记节点，但在动态图扰动下，这种尝试可能会严重退化。在本文中，我们将嘈杂的监督概括为一种自我监督的学习方法，然后提出了一种新颖的贝叶斯自学模型，即图形，以解决该问题。广泛的实验表明，图形不仅可以肯定地警告动态图上的扰动，而且还可以有效地恢复该图在这种扰动下的节点分类器的预测。这两个优势被证明是在五个公共图数据集中经过三个经典GCN的概括。
In recent years, plentiful evidence illustrates that Graph Convolutional Networks (GCNs) achieve extraordinary accomplishments on the node classification task. However, GCNs may be vulnerable to adversarial attacks on label-scarce dynamic graphs. Many existing works aim to strengthen the robustness of GCNs; for instance, adversarial training is used to shield GCNs against malicious perturbations. However, these works fail on dynamic graphs for which label scarcity is a pressing issue. To overcome label scarcity, self-training attempts to iteratively assign pseudo-labels to highly confident unlabeled nodes but such attempts may suffer serious degradation under dynamic graph perturbations. In this paper, we generalize noisy supervision as a kind of self-supervised learning method and then propose a novel Bayesian self-supervision model, namely GraphSS, to address the issue. Extensive experiments demonstrate that GraphSS can not only affirmatively alert the perturbations on dynamic graphs but also effectively recover the prediction of a node classifier when the graph is under such perturbations. These two advantages prove to be generalized over three classic GCNs across five public graph datasets.
