ABSTRACT
Graph-based Semi-Supervised Learning (SSL) algorithms tend to have a better performance than non-graph-based SSL approaches and have been successfully used in many areas. Embedding the social network in a geometric space simplifies the spreading process because it becomes a wavefront moving directly in that space. A technical problem remains which requires an extension to the previous signed spectral embedding technique. This chapter summarizes the Binary Class Graph Embedding (BCGE) for graph data with a limited class label set can be computed in steps. There are two ways in which data can be imbalanced. First, the number of records in one class might be much larger than the number in the other class(es). Second, the number of available labelled records in one class might be larger than the number in other class(es). If the structure of the original graph is consistent with the class labels, only a small repulsive force is needed to model the graph structure.
