TY - JOUR

T1 - Enhancing contrastive learning on learnable graph augmentation

AU - Xu, Yu

AU - Zhu, Guixiang

AU - Li, Huijia

AU - Cao, Jie

AU - Вукович, Дарко

N1 - Xu, Y., Zhu, G., Li, H., Wu, J., Cao, J., & Vukovic, D. (2026). Enhancing contrastive learning on learnable graph augmentation. IEEE Transactions on Big Data, 1–13. https://doi.org/10.1109/TBDATA.2026.3703236

PY - 2026

Y1 - 2026

N2 - Graph Contrastive Learning (GCL) has become an effective paradigm in graph representation learning by establishing contrastive relationships between nodes. Existing methods typically generate positive samples through manually designed graph data augmentation and obtain negative samples via random sampling. Suboptimal augmentation can corrupt the original graph topology, while false-negative samples introduce noise that degrades node representation quality. To address these issues, this paper proposes a novel graph contrastive representation learning framework called Enhancing Contrastive Learning with Augmentation (ECLA). First, we adopt a learnable augmentation module that generates adaptive augmented views through learnable edge weight adjustments. Second, we propose a joint metric method that integrates graph structural similarity and node feature similarity to model the deep semantic relationships between nodes, and based on this, we construct the distribution of positive and negative samples. Furthermore, we introduce a dual-weight contrastive loss function that enhances the contrastive learning intensity of semantically similar nodes through positive sample weights, while suppressing the negative impact of potential false-negative nodes through negative sample weights. ECLA jointly optimizes graph augmentation and representation learning in an end-to-end manner. Evaluations across diverse datasets show that ECLA consistently surpasses both leading graph contrastive methods and semi-supervised GNN baselines on node classification under severely limited label conditions. © 2015 IEEE.

AB - Graph Contrastive Learning (GCL) has become an effective paradigm in graph representation learning by establishing contrastive relationships between nodes. Existing methods typically generate positive samples through manually designed graph data augmentation and obtain negative samples via random sampling. Suboptimal augmentation can corrupt the original graph topology, while false-negative samples introduce noise that degrades node representation quality. To address these issues, this paper proposes a novel graph contrastive representation learning framework called Enhancing Contrastive Learning with Augmentation (ECLA). First, we adopt a learnable augmentation module that generates adaptive augmented views through learnable edge weight adjustments. Second, we propose a joint metric method that integrates graph structural similarity and node feature similarity to model the deep semantic relationships between nodes, and based on this, we construct the distribution of positive and negative samples. Furthermore, we introduce a dual-weight contrastive loss function that enhances the contrastive learning intensity of semantically similar nodes through positive sample weights, while suppressing the negative impact of potential false-negative nodes through negative sample weights. ECLA jointly optimizes graph augmentation and representation learning in an end-to-end manner. Evaluations across diverse datasets show that ECLA consistently surpasses both leading graph contrastive methods and semi-supervised GNN baselines on node classification under severely limited label conditions. © 2015 IEEE.

KW - Graph contrastive learning

KW - graph representation learning

KW - self-supervised learning

UR - https://eurekamag.com/research/108/117/108117565.php?srsltid=AfmBOoox-0S0T7cfpDGd5mjyOza5-tayri27Qk7gPlrb9E2ZTLsRJKYy

UR - https://www.mendeley.com/catalogue/2c9d112a-eccd-3e03-a535-af6f7a211480/

U2 - 10.1109/TBDATA.2026.3703236

DO - 10.1109/TBDATA.2026.3703236

M3 - Article

SP - 1

EP - 13

JO - IEEE Transactions on Big Data

JF - IEEE Transactions on Big Data

SN - 2332-7790

ER -