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 2103.12256cs.LGcs.AI
收藏

一般鲁棒图卷积网络的时空稀疏化

Spatio-Temporal Sparsification for General Robust Graph Convolution Networks

Central South University(中南大学)

Mingming Lu, Ya Zhang

摘要:

图神经网络(GNN)因其在各种图结构数据上的成功应用而引起越来越多的关注。然而,最近的研究表明,对抗攻击正在威胁GNN的功能。虽然已经提出了许多工作,以防止对抗攻击从不同的角度来看,他们中的大多数可以是强大的攻击,只有在特定的情况下。为了解决这种鲁棒泛化的不足,我们提出通过在GNN隐藏节点表示上应用时空稀疏化(称为ST稀疏)来防御对GNN的对抗攻击。ST-Sparse在精神上类似于Dropout正则化。通过对GCN作为目标GNN模型的深入实验评估,我们发现ST-Sparse的优点如下:(1)ST-Sparse在大多数情况下表现出防御性能的改善,因为它可以有效地提高鲁棒精度,最高可提高6%;(2)ST-Sparse通过与现有的防御方法相结合,展示了其强大的泛化能力,类似于将Dropout集成到各种深度学习模型中作为标准正则化技术;(3)ST-Sparse在干净数据集上也表现出普通的泛化能力,(ST-Sparse与原GCN的融合)的性能甚至优于原GCN,而其他三种代表性的防御方法都不如原GCN。

英文摘要:

Graph Neural Networks (GNNs) have attracted increasing attention due to its successful applications on various graph-structure data. However, recent studies have shown that adversarial attacks are threatening the functionality of GNNs. Although numerous works have been proposed to defend adversarial attacks from various perspectives, most of them can be robust against the attacks only on specific scenarios. To address this shortage of robust generalization, we propose to defend the adversarial attacks on GNN through applying the Spatio-Temporal sparsification (called ST-Sparse) on the GNN hidden node representation. ST-Sparse is similar to the Dropout regularization in spirit. Through intensive experiment evaluation with GCN as the target GNN model, we identify the benefits of ST-Sparse as follows: (1) ST-Sparse shows the defense performance improvement in most cases, as it can effectively increase the robust accuracy by up to 6\% improvement; (2) ST-Sparse illustrates its robust generalization capability by integrating with the existing defense methods, similar to the integration of Dropout into various deep learning models as a standard regularization technique; (3) ST-Sparse also shows its ordinary generalization capability on clean datasets, in that ST-SparseGCN (the integration of ST-Sparse and the original GCN) even outperform the original GCN, while the other three representative defense methods are inferior to the original GCN.

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。

↑