Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision-猫眼课题宝

DOI：

10.48550/arxiv.2203.03762

发表时间：

2022-03

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Jun Zhuang;M. Hasan

近年来，大量证据表明图卷积网络（GCN）在节点分类任务上取得了非凡的成就。然而，GCN 可能容易受到标签稀缺动态图的对抗性攻击。许多现有的工作旨在增强 GCN 的稳健性；例如，对抗性训练用于保护 GCN 免受恶意干扰。然而，这些工作在动态图上失败了，因为标签稀缺是一个紧迫的问题。为了克服标签稀缺性，自训练尝试迭代地将伪标签分配给高度置信的未标记节点，但这种尝试可能会在动态图扰动下遭受严重退化。在本文中，我们将噪声监督概括为一种自监督学习方法，然后提出一种新颖的贝叶斯自监督模型，即 GraphSS 来解决该问题。大量的实验表明，GraphSS不仅可以对动态图上的扰动做出肯定的警报，而且可以在图受到这种扰动时有效地恢复节点分类器的预测。事实证明，这两个优点可以推广到五个公共图数据集的三个经典 GCN 上。

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.

Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision

文献摘要

相似文献