LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Space

TL;DR

LAC introduces a novel graph contrastive learning framework with learnable augmentation in continuous space, improving node representations by adaptively augmenting graph data and optimizing pretext tasks based on an information-theoretic principle.

Contribution

The paper proposes a continuous space augmentation method and InfoBal principle, enhancing the effectiveness of graph contrastive learning in an unsupervised setting.

Findings

LAC outperforms state-of-the-art methods in node representation tasks.

Adaptive augmentation in continuous space improves contrastive learning effectiveness.

InfoBal enhances the consistency and diversity of augmented views.

Abstract

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.