Cover Image

Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Yongqi, Zhao, Jitao, He, Dongxiao, Jin, Di, Huang, Yuxiao, Wang, Zhen
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Str-GCL: Structural Commonsense Driven Graph Contrastive Learning
by: He, Dongxiao, et al.
Published: (2025)

GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks
by: He, Dongxiao, et al.
Published: (2026)

One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
by: Huang, Yongqi, et al.
Published: (2025)

CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts
by: Li, Peiyuan, et al.
Published: (2026)

Does Negative Sampling Matter? A Review with Insights into its Theory and Applications
by: Yang, Zhen, et al.
Published: (2024)

Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives
by: Wang, Zihu, et al.
Published: (2025)

Contrastive Learning with Negative Sampling Correction
by: Wang, Lu, et al.
Published: (2024)

Momentum Contrastive Learning with Enhanced Negative Sampling and Hard Negative Filtering
by: Hoang, Duy, et al.
Published: (2025)

MUG: Meta-path-aware Universal Heterogeneous Graph Pre-Training
by: Shan, Lianze, et al.
Published: (2026)

Supervised Contrastive Learning with Hard Negative Samples
by: Jiang, Ruijie, et al.
Published: (2022)

SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples
by: Shou, Yuntao, et al.
Published: (2024)

Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples
by: Yu, Jianxiang, et al.
Published: (2022)

GCL-GCN: Graphormer and Contrastive Learning Enhanced Attributed Graph Clustering Network
by: Li, Binxiong, et al.
Published: (2025)

GCL-Sampler: Discovering Kernel Similarity for Sampled GPU Simulation via Graph Contrastive Learning
by: Wang, Jiaqi, et al.
Published: (2026)

TopoGCL: Topological Graph Contrastive Learning
by: Chen, Yuzhou, et al.
Published: (2024)

AS-GCL: Asymmetric Spectral Augmentation on Graph Contrastive Learning
by: Liu, Ruyue, et al.
Published: (2025)

Multiplex Graph Contrastive Learning with Soft Negatives
by: Zhao, Zhenhao, et al.
Published: (2024)

Efficient Link Prediction via GNN Layers Induced by Negative Sampling
by: Wang, Yuxin, et al.
Published: (2023)

Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning
by: Di, Zixiang, et al.
Published: (2026)

Graph Contrastive Learning via Cluster-refined Negative Sampling for Semi-supervised Text Classification
by: Ai, Wei, et al.
Published: (2024)

Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding
by: Liang, Chundong, et al.
Published: (2026)

LocalGCL: Local-aware Contrastive Learning for Graphs
by: Jiang, Haojun, et al.
Published: (2024)

Layer-diverse Negative Sampling for Graph Neural Networks
by: Duan, Wei, et al.
Published: (2024)

From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning
by: Ali, Adnan, et al.
Published: (2024)

EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
by: Yau, Chung-Yiu, et al.
Published: (2024)

ID-MixGCL: Identity Mixup for Graph Contrastive Learning
by: Zhang, Gehang, et al.
Published: (2023)

HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning
by: Ji, Qirui, et al.
Published: (2025)

GCL-OT: Graph Contrastive Learning with Optimal Transport for Heterophilic Text-Attributed Graphs
by: Ren, Yating, et al.
Published: (2025)

Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-Collapse
by: Jiang, Ruijie, et al.
Published: (2023)

SOLA-GCL: Subgraph-Oriented Learnable Augmentation Method for Graph Contrastive Learning
by: Peng, Tianhao, et al.
Published: (2025)

CueGCL: Cluster-aware Personalized Self-Training for Unsupervised Graph Contrastive Learning
by: Li, Yuecheng, et al.
Published: (2023)

Diffusion-based Negative Sampling on Graphs for Link Prediction
by: Nguyen, Trung-Kien, et al.
Published: (2024)

Negative Metric Learning for Graphs
by: Zhao, Yiyang, et al.
Published: (2025)

Learning over Positive and Negative Edges with Contrastive Message Passing
by: Pao-Huang, Peter, et al.
Published: (2026)

Enhancing Link Prediction with Fuzzy Graph Attention Networks and Dynamic Negative Sampling
by: Xing, Jinming, et al.
Published: (2024)

Rethinking Contrastive Learning in Graph Anomaly Detection: A Clean-View Perspective
by: Jin, Di, et al.
Published: (2025)

SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for Recommendation
by: Lee, Chaejeong, et al.
Published: (2024)

Negative as Positive: Enhancing Out-of-distribution Generalization for Graph Contrastive Learning
by: Wang, Zixu, et al.
Published: (2024)

Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning
by: Yang, Zhaohui, et al.
Published: (2025)

Graph Contrastive Learning for Optimizing Sparse Data in Recommender Systems with LightGCL
by: Jatavallabha, Aravinda, et al.
Published: (2025)