通过对抗鲁棒性评估，自动剪掉易受攻击的图边，提升图学习的稳定性与效率。
Adversarial-Robustness-Guided Graph Pruning
- 基于谱鲁棒性评估，识别并剪除易受攻击的图边。
- 在谱聚类中实现更快的计算速度和更优的聚类质量。
- 适合需要高鲁棒性的图学习场景，如数据挖掘与异常检测。
图学习在流形学习、数据表示与分析、降维、聚类和可视化等任务中起核心作用。本文提出一种高度可扩展的对抗鲁棒性引导图剪枝框架，用于从数据中学习图结构。通过进行谱对抗鲁棒性评估，该方法旨在学习稀疏、无向的图结构，以增强底层算法对噪声和对抗扰动的抵抗能力。具体而言，显式识别并剪除最易受对抗攻击影响的边。我们采用谱聚类——一种典型的图基机器学习算法——来评估该框架。相比现有最先进方法，所提方法更具可扩展性，并显著提升了谱聚类的计算效率与解的质量。
原文摘要 · Abstract (English)
Graph learning plays a central role in many data mining and machine learning tasks, such as manifold learning, data representation and analysis, dimensionality reduction, clustering, and visualization. In this work, we propose a highly scalable, adversarial-robustness-guided graph pruning framework for learning graph topologies from data. By performing a spectral adversarial robustness evaluation, our method aims to learn sparse, undirected graphs that help the underlying algorithms resist noise and adversarial perturbations. In particular, we explicitly identify and prune edges that are most vulnerable to adversarial attacks. We use spectral clustering, one of the most representative graph-based machine learning algorithms, to evaluate the proposed framework. Compared with prior state-of-the-art graph learning approaches, the proposed method is more scalable and significantly improves both the computational efficiency and the solution quality of spectral clustering.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。