arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.12952cs.LGcs.CRcs.SIstat.ML
收藏

离散数据的有效鲁棒性证明:图、图像等的稀疏感知随机平滑

Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More

Technical University of Munich(慕尼黑工业大学)

Aleksandar Bojchevski, Johannes Gasteiger, Stephan Günnemann

摘要:

现有的技术用于证明离散数据的模型的鲁棒性,或者只适用于一小类模型,或者是以效率或紧密性为代价的一般性技术。此外,他们不占稀疏的输入,我们的研究结果表明,往往是必不可少的获得非平凡的保证。我们提出了一个模型不可知的证书的基础上的随机平滑框架,它包含了早期的工作,是紧密的,高效的,和稀疏意识。它的计算复杂性不依赖于离散类别的数量或输入的维度(例如图的大小),使其具有高度的可扩展性。我们展示了我们的方法在各种模型,数据集和任务上的有效性-特别强调了它在图神经网络中的应用。到目前为止,由于离散和非独立同分布,获得GNN的可证明保证一直很困难。图表数据的性质。我们的方法可以证明任何GNN,并处理对图结构和节点属性的扰动。

英文摘要:

Existing techniques for certifying the robustness of models for discrete data either work only for a small class of models or are general at the expense of efficiency or tightness. Moreover, they do not account for sparsity in the input which, as our findings show, is often essential for obtaining non-trivial guarantees. We propose a model-agnostic certificate based on the randomized smoothing framework which subsumes earlier work and is tight, efficient, and sparsity-aware. Its computational complexity does not depend on the number of discrete categories or the dimension of the input (e.g. the graph size), making it highly scalable. We show the effectiveness of our approach on a wide variety of models, datasets, and tasks -- specifically highlighting its use for Graph Neural Networks. So far, obtaining provable guarantees for GNNs has been difficult due to the discrete and non-i.i.d. nature of graph data. Our method can certify any GNN and handles perturbations to both the graph structure and the node attributes.

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。

↑