Saved in:
Bibliographic Details
Main Authors: Lin, Zhenyu, Li, Hongzheng, Shao, Yingxia, Ye, Guanhua, Li, Yawen, Xu, Quanqing
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.15355
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908097602125824
author Lin, Zhenyu
Li, Hongzheng
Shao, Yingxia
Ye, Guanhua
Li, Yawen
Xu, Quanqing
author_facet Lin, Zhenyu
Li, Hongzheng
Shao, Yingxia
Ye, Guanhua
Li, Yawen
Xu, Quanqing
contents Graph Contrastive Learning frameworks have demonstrated success in generating high-quality node representations. The existing research on efficient data augmentation methods and ideal pretext tasks for graph contrastive learning remains limited, resulting in suboptimal node representation in the unsupervised setting. In this paper, we introduce LAC, a graph contrastive learning framework with learnable data augmentation in an orthogonal continuous space. To capture the representative information in the graph data during augmentation, we introduce a continuous view augmenter, that applies both a masked topology augmentation module and a cross-channel feature augmentation module to adaptively augment the topological information and the feature information within an orthogonal continuous space, respectively. The orthogonal nature of continuous space ensures that the augmentation process avoids dimension collapse. To enhance the effectiveness of pretext tasks, we propose an information-theoretic principle named InfoBal and introduce corresponding pretext tasks. These tasks enable the continuous view augmenter to maintain consistency in the representative information across views while maximizing diversity between views, and allow the encoder to fully utilize the representative information in the unsupervised setting. Our experimental results show that LAC significantly outperforms the state-of-the-art frameworks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15355
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Space
Lin, Zhenyu
Li, Hongzheng
Shao, Yingxia
Ye, Guanhua
Li, Yawen
Xu, Quanqing
Machine Learning
Artificial Intelligence
Graph Contrastive Learning frameworks have demonstrated success in generating high-quality node representations. The existing research on efficient data augmentation methods and ideal pretext tasks for graph contrastive learning remains limited, resulting in suboptimal node representation in the unsupervised setting. In this paper, we introduce LAC, a graph contrastive learning framework with learnable data augmentation in an orthogonal continuous space. To capture the representative information in the graph data during augmentation, we introduce a continuous view augmenter, that applies both a masked topology augmentation module and a cross-channel feature augmentation module to adaptively augment the topological information and the feature information within an orthogonal continuous space, respectively. The orthogonal nature of continuous space ensures that the augmentation process avoids dimension collapse. To enhance the effectiveness of pretext tasks, we propose an information-theoretic principle named InfoBal and introduce corresponding pretext tasks. These tasks enable the continuous view augmenter to maintain consistency in the representative information across views while maximizing diversity between views, and allow the encoder to fully utilize the representative information in the unsupervised setting. Our experimental results show that LAC significantly outperforms the state-of-the-art frameworks.
title LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Space
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.15355