LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Space
This work addresses a bottleneck in graph representation learning for researchers and practitioners, offering a novel method to enhance unsupervised learning on graph data.
The paper tackles the problem of suboptimal node representations in unsupervised graph contrastive learning by introducing LAC, a framework with learnable data augmentation in an orthogonal continuous space and an information-theoretic pretext task, achieving significant performance improvements over state-of-the-art methods.
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.