arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.13038cs.LGstat.ML
收藏

一种具有动态调整图的鲁棒图注意力网络

A Robust graph attention network with dynamic adjusted Graph

National University of Defense Technology(国防科技大学)

Xianchen Zhou, Yaoyun Zeng, Hongxia Wang

摘要:

图注意力网络(GATs)是处理图数据的有用的深度学习模型。然而,最近的工作表明,经典的GAT是脆弱的对抗攻击。它会随着轻微的扰动而急剧退化。因此,如何增强GAT的鲁棒性是一个关键问题。为了提高GAT算法的鲁棒性,在对注意力机制进行改进的基础上,提出了鲁棒GAT算法(RoGAT)。与原GAT算法对不同边缘采用注意力机制,但仍对扰动敏感不同,RoGAT算法逐步增加了一个额外的动态注意力分数,提高了鲁棒性。首先,RoGAT修改的基础上的光滑性假设,这是很常见的普通图的边的重量。其次,RoGAT进一步修正特征以抑制特征噪声。然后,通过动态边的权重生成额外的注意力分数,并可用于减少对抗攻击的影响。针对引文数据的有针对性和无针对性攻击的不同实验表明,RoGAT优于大多数最近的防御方法。

英文摘要:

Graph Attention Networks(GATs) are useful deep learning models to deal with the graph data. However, recent works show that the classical GAT is vulnerable to adversarial attacks. It degrades dramatically with slight perturbations. Therefore, how to enhance the robustness of GAT is a critical problem. Robust GAT(RoGAT) is proposed in this paper to improve the robustness of GAT based on the revision of the attention mechanism. Different from the original GAT, which uses the attention mechanism for different edges but is still sensitive to the perturbation, RoGAT adds an extra dynamic attention score progressively and improves the robustness. Firstly, RoGAT revises the edges weight based on the smoothness assumption which is quite common for ordinary graphs. Secondly, RoGAT further revises the features to suppress features' noise. Then, an extra attention score is generated by the dynamic edge's weight and can be used to reduce the impact of adversarial attacks. Different experiments against targeted and untargeted attacks on citation data on citation data demonstrate that RoGAT outperforms most of the recent defensive methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑