RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning
This addresses a gap in graph representation learning for researchers, though it appears incremental as it builds on existing contrastive learning methods.
The paper tackles the problem of non-aligned node-node graph contrastive learning by proposing RoSA, which uses earth mover's distance and adversarial training to outperform existing frameworks on homophilous, non-homophilous, and dynamic graphs.
Graph contrastive learning has gained significant progress recently. However, existing works have rarely explored non-aligned node-node contrasting. In this paper, we propose a novel graph contrastive learning method named RoSA that focuses on utilizing non-aligned augmented views for node-level representation learning. First, we leverage the earth mover's distance to model the minimum effort to transform the distribution of one view to the other as our contrastive objective, which does not require alignment between views. Then we introduce adversarial training as an auxiliary method to increase sampling diversity and enhance the robustness of our model. Experimental results show that RoSA outperforms a series of graph contrastive learning frameworks on homophilous, non-homophilous and dynamic graphs, which validates the effectiveness of our work. To the best of our awareness, RoSA is the first work focuses on the non-aligned node-node graph contrastive learning problem. Our codes are available at: \href{https://github.com/ZhuYun97/RoSA}{\texttt{https://github.com/ZhuYun97/RoSA}}