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

• URL: http://arxiv.org/abs/2604.14746v1
• Date: Thu, 16 Apr 2026 07:57:11 GMT
• Title: Disentangle-then-Refine: LLM-Guided Decoupling and Structure-Aware Refinement for Graph Contrastive Learning
• Abstract summary: Conventional Graph Contrastive Learning (GCL) on Text-Attributed Graphs (TAGs) relies on blind augmentations, inadvertently entangling task-relevant signals with noise.<n>We propose SDM-SCR, a robust framework anchored in Approximate Orthogonal Decomposition.
• Score: 8.080589414732982
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models [59.414664850109155]
  Diffusion large language models (D-LLMs) have emerged as a promising paradigm for text generation.<n>D-LLMs remain vulnerable to hallucinations, where fluent outputs may contain factually incorrect or unsupported content.
  arXiv  Detail & Related papers  (2026-07-24T06:45:43Z)
• Beyond Noisy Signals: Dual-Level Denoising for Multi-modal Sequential Recommendation [6.902443075506667]
  We propose textbfDual-level textbfDenoising textbfMulti-modal textbfSequential textbfRecommendation framework.
  arXiv  Detail & Related papers  (2026-07-21T07:06:06Z)
• Hierarchical Policy Learning via Spectral Decomposition [58.65543693788772]
  We identify a semantic decomposition in robot action sequences, separating task-level motion intent from execution-level refinements.<n>Motivated by this structure, we propose Causal Spectral Policy (CSP), which models action generation as a causal coarse-to-fine process.<n>CSP consistently outperforms strong baselines on precision-sensitive manipulation tasks.
  arXiv  Detail & Related papers  (2026-06-28T19:22:40Z)
• Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations [24.706105488382818]
  Implicit Neural Representations (INRs) have been proven successful in encoding continuous signals through coordinate-based networks.<n>They face a spectral dilemma: periodic activations capture fine details but act as all-pass filters that memorise noise, while spatially compact activations regularise effectively but suffer from low-frequency bias.<n>We propose to model each neuron's activation as the steady-state response of a sinusoidally-forced damped harmonic oscillator.
  arXiv  Detail & Related papers  (2026-06-22T11:59:47Z)
• Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs [33.559566576032964]
  We propose Convex Gate, a speech-to-LLM bridge that constrains all speech representations to lie within the LLM's input embedding manifold.<n>Across automatic speech recognition and emotion recognition, C-Gate achieves strong joint performance.<n>Results suggest that geometry, rather than token discreteness, is the fundamental design factor in speech-to-LLM interfaces.
  arXiv  Detail & Related papers  (2026-06-08T11:38:40Z)
• Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation [58.33732779555114]
  We argue that the key bottleneck is a representation-level failure caused by two coupled heterogeneities.<n>We propose Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation (SpectraMB)<n>SpectraMB achieves the best results in most evaluation settings and exhibits improved robustness under noisy interactions.
  arXiv  Detail & Related papers  (2026-06-01T15:58:13Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Systematic Integration of Digital Twins and Constrained LLMs for Interpretable Cyber-Physical Anomaly Detection [0.0]
  Cyber attacks targeting Industrial Control Systems (ICS) have become increasingly sophisticated and hard to identify.<n>Detecting such attacks requires integrating low-level behavioral cues with high-level semantic interpretation.<n>This paper presents a Digital Twin (DT)-driven hybrid detection approach.
  arXiv  Detail & Related papers  (2026-04-04T16:38:12Z)
• Variational Rectification Inference for Learning with Noisy Labels [74.85528327499662]
  We propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions.<n>VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable.<n>By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function.
  arXiv  Detail & Related papers  (2026-03-18T01:25:08Z)
• Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models [24.141149551300817]
  Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Networks to generalize to unseen domains or label spaces.<n>We introduce GraphSSR, a novel framework designed for adaptive subgraph extraction and denoising in zero-shot LLM-based graph reasoning.
  arXiv  Detail & Related papers  (2026-03-03T12:47:44Z)
• The Malignant Tail: Spectral Segregation of Label Noise in Over-Parameterized Networks [0.0]
  We experimentally isolate the Malignant Tail, a failure mode where networks functionally segregate signal and noise.<n>We show that untrained networks actively segregate noise, allowing post-hoc Explicit Spectral Truncation to surgically prune the noise-dominated subspace.<n>Our findings suggest that under label noise, excess spectral capacity is not harmless redundancy but a latent structural liability.
  arXiv  Detail & Related papers  (2026-03-02T16:39:42Z)
• Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models [53.79667447811139]
  We show that a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal.<n>These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader estimation.
  arXiv  Detail & Related papers  (2026-02-04T15:25:02Z)
• Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classification [5.658568324275769]
  We propose NAR, a noise-adaptive regularization method that distinguishes between additive and subtractive noise.<n> NAR consistently improves robustness compared with existing methods.<n>Performance improvements are most pronounced under subtractive and mixed noise.
  arXiv  Detail & Related papers  (2026-01-13T11:16:45Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signals [10.85580316542761]
  Hallucination remains a critical barrier for deploying large language models (LLMs) in reliability-sensitive applications.<n>We propose HSAD (Hidden Signal Analysis-based Detection), a novel hallucination detection framework that models the temporal dynamics of hidden representations.<n>Across multiple benchmarks, including TruthfulQA, HSAD achieves over 10 percentage points improvement compared to prior state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-16T15:08:19Z)
• Autoregressive Speech Synthesis without Vector Quantization [135.4776759536272]
  We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS)<n>MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition.<n>MELLE mitigates robustness issues by avoiding the inherent flaws of sampling vector-quantized codes.
  arXiv  Detail & Related papers  (2024-07-11T14:36:53Z)
• Simultaneous Denoising and Dereverberation Using Deep Embedding Features [64.58693911070228]
  We propose a joint training method for simultaneous speech denoising and dereverberation using deep embedding features. At the denoising stage, the DC network is leveraged to extract noise-free deep embedding features. At the dereverberation stage, instead of using the unsupervised K-means clustering algorithm, another neural network is utilized to estimate the anechoic speech.
  arXiv  Detail & Related papers  (2020-04-06T06:34:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.