Disentangle-then-Refine: LLM-Guided Decoupling and Structure-Aware Refinement for Graph Contrastive Learning

arXiv:2604.14746v1 Announce Type: new Abstract: Conventional Graph Contrastive Learning (GCL) on Text-Attributed Graphs (TAGs) relies on blind stochastic augmentations, inadvertently entangling task-relevant signals with noise. We propose SDM-SCR, a robust framework anchored in Approximate Orthogonal Decomposition. First, the Semantic Decoupling Module (SDM) leverages the instruction-following capability of Large Language Models (LLMs) to actively parse raw attributes into asymmetric, task-orien