Positive-Unlabeled Node Classification with Structure-aware Graph Learning
It addresses a challenging setting in graph learning with applications like pandemic prediction, but it is incremental as it builds on existing PU classification by incorporating graph structure.
The paper tackles positive-unlabeled node classification on graphs by proposing a structure-aware method, achieving superior performance over state-of-the-art methods in empirical evaluations.
Node classification on graphs is an important research problem with many applications. Real-world graph data sets may not be balanced and accurate as assumed by most existing works. A challenging setting is positive-unlabeled (PU) node classification, where labeled nodes are restricted to positive nodes. It has diverse applications, e.g., pandemic prediction or network anomaly detection. Existing works on PU node classification overlook information in the graph structure, which can be critical. In this paper, we propose to better utilize graph structure for PU node classification. We first propose a distance-aware PU loss that uses homophily in graphs to introduce more accurate supervision. We also propose a regularizer to align the model with graph structure. Theoretical analysis shows that minimizing the proposed loss also leads to minimizing the expected loss with both positive and negative labels. Extensive empirical evaluation on diverse graph data sets demonstrates its superior performance over existing state-of-the-art methods.