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

arXiv: https://arxiv.org/abs/2604.14746 · HTML: https://mlsanity.com/paper/2604.14746/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2007.02901/) (2020)
- [Large-Scale Representation Learning on Graphs via Bootstrapping](https://mlsanity.com/paper/2102.06514/) (2021)
- [SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation](https://mlsanity.com/paper/2202.03104/) (2022)
- [Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction](https://mlsanity.com/paper/2111.00064/) (2021)
- [Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks](https://mlsanity.com/paper/2006.13866/) (2020)
- [Deep Representation Learning for Social Network Analysis](https://mlsanity.com/paper/1904.08547/) (2019)
- [Towards Graph Contrastive Learning: A Survey and Beyond](https://mlsanity.com/paper/2405.11868/) (2024)
- [HomoGCL: Rethinking Homophily in Graph Contrastive Learning](https://mlsanity.com/paper/2306.09614/) (2023)
- [GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Models](https://mlsanity.com/paper/2406.11945/) (2024)
- [Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models](https://mlsanity.com/paper/2407.18999/) (2024)
- [Leveraging Graph Structures to Detect Hallucinations in Large Language Models](https://mlsanity.com/paper/2407.04485/) (2024)
- [ERGNN: Spectral Graph Neural Network With Explicitly-Optimized Rational Graph Filters](https://mlsanity.com/paper/2412.19106/) (2024)
- [LATEX-GCL: Large Language Models (LLMs)-Based Data Augmentation for Text-Attributed Graph Contrastive Learning](https://mlsanity.com/paper/2409.01145/) (2024)
- [InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning](https://mlsanity.com/paper/2505.06282/) (2025)
- [Refining Interactions: Enhancing Anisotropy in Graph Neural Networks with Language Semantics](https://mlsanity.com/paper/2504.01429/) (2025)
- [Benchmarking Fairness-aware Graph Neural Networks in Knowledge Graphs](https://mlsanity.com/paper/2510.18473/) (2025)

## Abstract (arXiv)

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.