GMCL: Graph Mask Contrastive Learning for Self-Supervised Graph Representation Learning

Graph self-supervised learning is a task replete with potential. Previously, mainstream approaches in graph self-supervised learning were based on contrastive or generative tasks to extract graph embeddings, achieving commendable performance in downstream tasks such as node classification. However, these two methods have their respective strengths and limitations: (i) contrastive graph learning excels at capturing discriminative features of the graph but is more prone to overlooking structural representations of the graph itself; (ii) generative methods prioritize learning reconstructive features but struggle with large graphs and are susceptible to overfitting. Consequently, several simplistic fusion methods have been proposed, integrating encoded features from both approaches through concatenation, addition, or attention mechanisms for downstream tasks. However, these methods tend to be overly coarse, neglecting some unique information present in both categories of methods. To enhance the synergy of these two methods, we propose an edge perturbation data augmentation method to prevent the generation of spurious positive samples and a feature imputation decoder to complement contrastive features. We assess the model's performance on two downstream tasks in graph representation learning, and experimental results demonstrate that our proposed method outperforms baseline methods on ten publicly available datasets.