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

TL;DR

This paper introduces SDM-SCR, a novel framework for graph contrastive learning that uses LLM-guided semantic decoupling and spectral regularization to improve signal disentanglement and achieve state-of-the-art results.

Contribution

It proposes a new disentangle-then-refine approach leveraging LLMs and spectral filtering for more effective graph contrastive learning.

Findings

SDM-SCR outperforms existing methods in accuracy.

The framework enhances efficiency in graph contrastive learning.

Semantic decoupling reduces LLM hallucinations effectively.

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-oriented signal and noise views. This shifts the paradigm from random perturbation to semantic-aware disentanglement. Subsequently, Semantic Consistency Regularization (SCR) exploits the spectral observation that semantic signals are topologically smooth while residual noise is high-frequency. SCR functions as a selective spectral filter, enforcing consistency only on the signal subspace to eliminate LLM hallucinations without over-smoothing. This ``Disentangle-then-Refine'' mechanism ensures rigorous signal purification. Extensive experiments demonstrate that SDM-SCR achieves SOTA performance in accuracy and efficiency.