SPGCL: 通过SVD引导的结构扰动实现简单而强大的图对比学习
SPGCL: Simple yet Powerful Graph Contrastive Learning via SVD-Guided Structural Perturbation
AI总结：
SPGCL通过SVD引导的结构扰动提升图对比学习的鲁棒性和准确性，优于现有方法。
摘要：
图神经网络（GNNs）对来自对抗攻击或缺陷的结构噪声敏感。现有的图对比学习（GCL）方法通常依赖于随机扰动（例如边删除）来增加多样性或频谱增强（例如SVD）来保持结构先验。然而，随机扰动是结构无关的，可能会移除关键边，而基于SVD的观点往往缺乏足够的多样性。将这些范式整合具有挑战性，因为它们分别在离散边删除和连续矩阵分解上操作。我们提出了SPGCL，一种通过SVD引导的结构扰动实现鲁棒GCL的框架。利用最近开发的一种基于SVD的方法，该方法将结构扰动理论推广到任意图中，我们设计了两种阶段策略：（1）轻量级随机边删除以注入多样性，（2）截断SVD以推导一个结构感知的评分矩阵以稀疏恢复前P条边。这种整合提供了三个优势：（1）对偶然删除的鲁棒性，因为重要边可以通过SVD引导评分恢复；（2）补充缺失的链接，通过引入语义有意义的边创建更具信息量的对比视图；（3）可控的结构差异，确保对比信号源于语义差异而不是边数差距。此外，我们结合了一个对比融合模块，该模块具有全局相似性约束以对齐嵌入。在十个基准数据集上的广泛实验表明，SPGCL一致提高了GNN的鲁棒性和准确性，优于最先进的GCL和结构学习方法，验证了其在整合先前不同范式方面的有效性。
英文摘要：
Graph Neural Networks (GNNs) are sensitive to structural noise from adversarial attacks or imperfections. Existing graph contrastive learning (GCL) methods typically rely on either random perturbations (e.g., edge dropping) for diversity or spectral augmentations (e.g., SVD) to preserve structural priors. However, random perturbations are structure-agnostic and may remove critical edges, while SVD-based views often lack sufficient diversity. Integrating these paradigms is challenging as they operate on discrete edge removal and continuous matrix factorization, respectively.We propose SPGCL, a framework for robust GCL via SVD-guided structural perturbation. Leveraging a recently developed SVD-based method that generalizes structural perturbation theory to arbitrary graphs, we design a two-stage strategy: (1) lightweight stochastic edge removal to inject diversity, and (2) truncated SVD to derive a structure-aware scoring matrix for sparse top-$P$ edge recovery. This integration offers three advantages: (1) Robustness to accidental deletion, as important edges can be recovered by SVD-guided scoring; (2) Enrichment with missing links, creating more informative contrastive views by introducing semantically meaningful edges; and (3) Controllable structural discrepancy, ensuring contrastive signals stem from semantic differences rather than edge-number gaps.Furthermore, we incorporate a contrastive fusion module with a global similarity constraint to align embeddings. Extensive experiments on ten benchmark datasets demonstrate that SPGCL consistently improves the robustness and accuracy of GNNs, outperforming state-of-the-art GCL and structure learning methods, validating its effectiveness in integrating previously disparate paradigms.
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。
