A Graph-Based Projection Approach for Semi-supervised Clustering

This paper proposes a graph-based projection approach for semi-supervised clustering based on pairwise relations among instances. In our approach, the entire data is represented as an edge-weighted graph with the pairwise similarities among instances. Graph representation enables to deal with two kinds of pairwise constraints as well as pairwise similarities over the same unified representation. Then, in order to reflect the pairwise constraints on the clustering process, the graph is modified by contraction in graph theory and graph Laplacian in spectral graph theory. By exploiting the constraints as well as similarities among instances, the entire data are projected onto a Subspace via the modified graph, and data clustering is conducted over the projected representation. The proposed approach is evaluated over several real world datasets. The results are encouraging and indicate the effectiveness of the proposed approach.