提出新对比学习框架，提升图表示对结构扰动的鲁棒性
Cheeger--Hodge Contrastive Learning for Structurally Robust Graph Representation Learning
- 基于切赫-霍奇联合签名，融合全局连通性与高阶结构信息
- 在多个基准上性能超越现有方法，抗结构扰动能力更强
- 适合需要稳定图嵌入的场景，如节点分类、图匹配
图对比学习（GCL）已成为无监督图表示学习的重要框架。然而，仅依赖增强设计来定义学习到的不变性，在结构扰动下可能表现脆弱。为此，我们提出切赫-霍奇对比学习（CHCL），通过在不同增强视图间对齐一个结构稳定且具备鲁棒性的切赫-霍奇联合签名，实现更稳健的图表示学习。该签名结合了基于代数连通性λ₂的切赫启发式连通性度量与一阶霍奇拉普拉斯算子的低频谱信息，从而同时捕捉全局连通性与高阶结构特征。通过在不同增强视图间对齐编码器表示与该联合签名，CHCL学习到的图嵌入对局部结构扰动具有强鲁棒性。在标准基准和迁移设置上的大量实验表明，CHCL在性能、鲁棒性和泛化能力方面均持续优于现有方法。
原文摘要 · Abstract (English)
Graph Contrastive Learning (GCL) has emerged as a prominent framework for unsupervised graph representation learning. However, relying on augmentation design alone to define the invariances learned by GCL can be brittle under structural perturbations. To address this issue, we propose Cheeger--Hodge Contrastive Learning (CHCL), a framework that aligns a perturbation-stable Cheeger--Hodge joint signature across augmented views for robust graph representation learning. The proposed signature combines a Cheeger-inspired connectivity signature derived from the algebraic connectivity \(λ_2\) with the low-frequency spectrum of the 1-Hodge Laplacian, thereby capturing both global connectivity and higher-order structural information. By aligning encoder representations with the proposed Cheeger--Hodge joint signature across augmented views, CHCL learns graph embeddings that are robust to local structural perturbations. Extensive experiments on standard benchmarks, transfer settings demonstrate that CHCL consistently improves performance, robustness, and generalization.
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。