Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning
This addresses the need for label-free learning in graph-structured data, which is incremental as it builds on existing contrastive and Siamese techniques.
The paper tackles the problem of graph representation learning without relying on labels by proposing a self-supervised approach that combines Siamese networks with multi-scale contrastive learning, achieving new state-of-the-art results on five real-world datasets and surpassing some semi-supervised methods by large margins.
Graph representation learning plays a vital role in processing graph-structured data. However, prior arts on graph representation learning heavily rely on labeling information. To overcome this problem, inspired by the recent success of graph contrastive learning and Siamese networks in visual representation learning, we propose a novel self-supervised approach in this paper to learn node representations by enhancing Siamese self-distillation with multi-scale contrastive learning. Specifically, we first generate two augmented views from the input graph based on local and global perspectives. Then, we employ two objectives called cross-view and cross-network contrastiveness to maximize the agreement between node representations across different views and networks. To demonstrate the effectiveness of our approach, we perform empirical experiments on five real-world datasets. Our method not only achieves new state-of-the-art results but also surpasses some semi-supervised counterparts by large margins. Code is made available at https://github.com/GRAND-Lab/MERIT