Contrastive Disentangled Learning on Graph for Node Classification
This work addresses the challenge of label scarcity in graph learning for researchers in graph neural networks, though it appears incremental by building on existing contrastive learning methods.
The authors tackled the problem of learning disentangled node representations for graph-structured data without heavy reliance on labels, achieving improved performance in node classification tasks on citation networks compared to various baselines.
Contrastive learning methods have attracted considerable attention due to their remarkable success in analyzing graph-structured data. Inspired by the success of contrastive learning, we propose a novel framework for contrastive disentangled learning on graphs, employing a disentangled graph encoder and two carefully crafted self-supervision signals. Specifically, we introduce a disentangled graph encoder to enforce the framework to distinguish various latent factors corresponding to underlying semantic information and learn the disentangled node embeddings. Moreover, to overcome the heavy reliance on labels, we design two self-supervision signals, namely node specificity and channel independence, which capture informative knowledge without the need for labeled data, thereby guiding the automatic disentanglement of nodes. Finally, we perform node classification tasks on three citation networks by using the disentangled node embeddings, and the relevant analysis is provided. Experimental results validate the effectiveness of the proposed framework compared with various baselines.