可认证鲁棒的图对比学习
Certifiably Robust Graph Contrastive Learning
AI总结：
针对图对比学习易受对抗攻击且缺乏可认证鲁棒性研究的问题，本文提出首个可认证鲁棒框架，通过统一评估准则、RES随机边丢弃平滑技术及配套训练方法，为任意GCL模型提供可证明的鲁棒性且能保留至下游任务，实验验证了方法的有效性。
摘要：
图对比学习（Graph Contrastive Learning, GCL）已成为一种流行的无监督图表示学习方法。然而，已有研究表明GCL在图结构和节点属性上都容易受到对抗攻击。尽管已有研究提出了多种经验性方法来增强GCL的鲁棒性，但GCL的可认证鲁棒性仍未被探索。本文提出了首个GCL领域的可认证鲁棒框架。具体而言，我们首先提出了一个统一的准则，用于评估和认证GCL的鲁棒性。随后我们引入了一种新技术RES（随机边丢弃平滑，Randomized Edgedrop Smoothing），可为任意GCL模型提供可认证的鲁棒性，且这种认证鲁棒性可被证明能保留在下游任务中。此外，我们还提出了一种用于鲁棒GCL的有效训练方法。在真实世界数据集上的大量实验证明，本文提出的方法在提供有效可认证鲁棒性、增强任意GCL模型鲁棒性方面均具备有效性。RES的源代码可在https://github.com/ventr1c/RES-GCL获取。
英文摘要：
Graph Contrastive Learning (GCL) has emerged as a popular unsupervised graph representation learning method. However, it has been shown that GCL is vulnerable to adversarial attacks on both the graph structure and node attributes. Although empirical approaches have been proposed to enhance the robustness of GCL, the certifiable robustness of GCL is still remain unexplored. In this paper, we develop the first certifiably robust framework in GCL. Specifically, we first propose a unified criteria to evaluate and certify the robustness of GCL. We then introduce a novel technique, RES (Randomized Edgedrop Smoothing), to ensure certifiable robustness for any GCL model, and this certified robustness can be provably preserved in downstream tasks. Furthermore, an effective training method is proposed for robust GCL. Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed method in providing effective certifiable robustness and enhancing the robustness of any GCL model. The source code of RES is available at https://github.com/ventr1c/RES-GCL.
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。
