Structure-augmentation and Attribute-aware Graph Contrastive Learning with Weak Information

Graph neural networks (GNNs) have shown impressive performance in many graph learning tasks. Traditional GNNs assume that input data is complete, however, GNNs are typically constrained by weak information (such as incomplete structure, incomplete features, and insufficient labels). Moreover, GNNs rely on the homophily assumption of the network, which ignores the node similarity in the attribute space. In this paper, we propose a Structure-augmentation and Attribute-aware Graph Contrastive Learning with Weak Information method (SA-GCL), which integrates multiple weak signals and processes them through unified modeling and joint contrastive mechanisms. Specifically, we generate the feature completion graph, which utilizes the feature information of the long-range neighbors to complement the original nodes, to effectively alleviate the weak feature problem. To address the weak structure problem, we enhance the original graph and further construct the global structure graph that is not limited to first-order neighbors, fully capturing the global topological relationships in the graph. In addition, to mitigate the non-homophilic problem, we retain the attribute information of the original graph and generate the attribute-aware graph based on the attribute-association relationships among nodes. Then, we input the above graph data into the GNN encoder and achieve collaborative contrastive learning of multiple weak signals through joint contrastive learning under four different views. Finally, the SA-GCL model maximizes the common information between similar instances, which effectively mitigates the weak label problem. Experimental results on real datasets with different levels of homophily show that our method outperforms state-of-the-art graph representation learning approaches on both node classification and link prediction tasks.