Saved in:
Bibliographic Details
Main Authors: Huang, Yixuan, Chen, Jiawei, Zhang, Shengfan, Cao, Zongsheng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.16800
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914402663399424
author Huang, Yixuan
Chen, Jiawei
Zhang, Shengfan
Cao, Zongsheng
author_facet Huang, Yixuan
Chen, Jiawei
Zhang, Shengfan
Cao, Zongsheng
contents Collaborative filtering (CF) recommendation has been significantly advanced by integrating Graph Neural Networks (GNNs) and Graph Contrastive Learning (GCL). However, (i) random edge perturbations often distort critical structural signals and degrade semantic consistency across augmented views, and (ii) data sparsity hampers the propagation of collaborative signals, limiting generalization. To tackle these challenges, we propose RaDAR (Relation-aware Diffusion-Asymmetric Graph Contrastive Learning Framework for Recommendation Systems), a novel framework that combines two complementary view generation mechanisms: a graph generative model to capture global structure and a relation-aware denoising model to refine noisy edges. RaDAR introduces three key innovations: (1) asymmetric contrastive learning with global negative sampling to maintain semantic alignment while suppressing noise; (2) diffusion-guided augmentation, which employs progressive noise injection and denoising for enhanced robustness; and (3) relation-aware edge refinement, dynamically adjusting edge weights based on latent node semantics. Extensive experiments on three public benchmarks demonstrate that RaDAR consistently outperforms state-of-the-art methods, particularly under noisy and sparse conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16800
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RaDAR: Relation-aware Diffusion-Asymmetric Graph Contrastive Learning for Recommendation
Huang, Yixuan
Chen, Jiawei
Zhang, Shengfan
Cao, Zongsheng
Machine Learning
Collaborative filtering (CF) recommendation has been significantly advanced by integrating Graph Neural Networks (GNNs) and Graph Contrastive Learning (GCL). However, (i) random edge perturbations often distort critical structural signals and degrade semantic consistency across augmented views, and (ii) data sparsity hampers the propagation of collaborative signals, limiting generalization. To tackle these challenges, we propose RaDAR (Relation-aware Diffusion-Asymmetric Graph Contrastive Learning Framework for Recommendation Systems), a novel framework that combines two complementary view generation mechanisms: a graph generative model to capture global structure and a relation-aware denoising model to refine noisy edges. RaDAR introduces three key innovations: (1) asymmetric contrastive learning with global negative sampling to maintain semantic alignment while suppressing noise; (2) diffusion-guided augmentation, which employs progressive noise injection and denoising for enhanced robustness; and (3) relation-aware edge refinement, dynamically adjusting edge weights based on latent node semantics. Extensive experiments on three public benchmarks demonstrate that RaDAR consistently outperforms state-of-the-art methods, particularly under noisy and sparse conditions.
title RaDAR: Relation-aware Diffusion-Asymmetric Graph Contrastive Learning for Recommendation
topic Machine Learning
url https://arxiv.org/abs/2603.16800