Cheeger--Hodge Contrastive Learning for Structurally Robust Graph Representation Learning
For graph representation learning, CHCL addresses brittleness to structural perturbations in contrastive learning, offering a more robust framework.
Cheeger-Hodge Contrastive Learning (CHCL) improves graph representation robustness to structural perturbations by aligning a perturbation-stable joint signature across augmented views, achieving consistent gains in performance and generalization on benchmarks.
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.