Saved in:
Bibliographic Details
Main Authors: Hsieh, Chou-Ying, Jang, Chun-Fu, Hsieh, Cheng-En, Chen, Qian-Hui, Kuo, Sy-Yen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.13650
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915293417177088
author Hsieh, Chou-Ying
Jang, Chun-Fu
Hsieh, Cheng-En
Chen, Qian-Hui
Kuo, Sy-Yen
author_facet Hsieh, Chou-Ying
Jang, Chun-Fu
Hsieh, Cheng-En
Chen, Qian-Hui
Kuo, Sy-Yen
contents Graphs serve as versatile data structures in numerous real-world domains-including social networks, molecular biology, and knowledge graphs-by capturing intricate relational information among entities. Among graph-based learning techniques, Graph Contrastive Learning (GCL) has gained significant attention for its ability to derive robust, self-supervised graph representations through the contrasting of positive and negative sample pairs. However, a critical challenge lies in ensuring high-quality positive pairs so that the intrinsic semantic and structural properties of the original graph are preserved rather than distorted. To address this issue, we propose SRGCL (Self-Reinforced Graph Contrastive Learning), a novel framework that leverages the model's own encoder to dynamically evaluate and select high-quality positive pairs. We designed a unified positive pair generator employing multiple augmentation strategies, and a selector guided by the manifold hypothesis to maintain the underlying geometry of the latent space. By adopting a probabilistic mechanism for selecting positive pairs, SRGCL iteratively refines its assessment of pair quality as the encoder's representational power improves. Extensive experiments on diverse graph-level classification tasks demonstrate that SRGCL, as a plug-in module, consistently outperforms state-of-the-art GCL methods, underscoring its adaptability and efficacy across various domains.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13650
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-Reinforced Graph Contrastive Learning
Hsieh, Chou-Ying
Jang, Chun-Fu
Hsieh, Cheng-En
Chen, Qian-Hui
Kuo, Sy-Yen
Machine Learning
Artificial Intelligence
Graphs serve as versatile data structures in numerous real-world domains-including social networks, molecular biology, and knowledge graphs-by capturing intricate relational information among entities. Among graph-based learning techniques, Graph Contrastive Learning (GCL) has gained significant attention for its ability to derive robust, self-supervised graph representations through the contrasting of positive and negative sample pairs. However, a critical challenge lies in ensuring high-quality positive pairs so that the intrinsic semantic and structural properties of the original graph are preserved rather than distorted. To address this issue, we propose SRGCL (Self-Reinforced Graph Contrastive Learning), a novel framework that leverages the model's own encoder to dynamically evaluate and select high-quality positive pairs. We designed a unified positive pair generator employing multiple augmentation strategies, and a selector guided by the manifold hypothesis to maintain the underlying geometry of the latent space. By adopting a probabilistic mechanism for selecting positive pairs, SRGCL iteratively refines its assessment of pair quality as the encoder's representational power improves. Extensive experiments on diverse graph-level classification tasks demonstrate that SRGCL, as a plug-in module, consistently outperforms state-of-the-art GCL methods, underscoring its adaptability and efficacy across various domains.
title Self-Reinforced Graph Contrastive Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.13650