LocalGCL: Local-aware Contrastive Learning for Graphs
This addresses a specific bottleneck in graph representation learning for self-supervised tasks, but it appears incremental as it builds on existing contrastive learning frameworks.
The paper tackles the problem of graph contrastive learning overemphasizing global patterns by neglecting local structures, proposing LocalGCL to supplementarily capture local information with masking-based modeling, and shows it outperforms state-of-the-art methods in experiments.
Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings. Meanwhile, the time-consuming and costly process of annotating graph labels manually prompts the growth of self-supervised learning (SSL) techniques. As a dominant approach of SSL, Contrastive learning (CL) learns discriminative representations by differentiating between positive and negative samples. However, when applied to graph data, it overemphasizes global patterns while neglecting local structures. To tackle the above issue, we propose \underline{Local}-aware \underline{G}raph \underline{C}ontrastive \underline{L}earning (\textbf{\methnametrim}), a self-supervised learning framework that supplementarily captures local graph information with masking-based modeling compared with vanilla contrastive learning. Extensive experiments validate the superiority of \methname against state-of-the-art methods, demonstrating its promise as a comprehensive graph representation learner.