SPGCL: Simple yet Powerful Graph Contrastive Learning via SVD-Guided Structural Perturbation

TL;DR

SPGCL introduces a novel SVD-guided structural perturbation framework for graph contrastive learning, enhancing robustness and diversity of contrastive views by combining stochastic edge removal with SVD-based edge recovery.

Contribution

The paper presents a new SVD-guided structural perturbation method that effectively integrates random perturbations and spectral analysis for more robust graph contrastive learning.

Findings

SPGCL outperforms existing methods on ten benchmark datasets.

The framework improves robustness against structural noise.

It enhances the accuracy of GNNs in various tasks.

Abstract

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.