Joint Graph and Vertex Importance Learning

To account for the difficulty associated with singular CGL matrices in inverse covariance estimation, the objective In this paper, we explore the topic of graph learning from the function is oftentimes modified [5, 9-12]. However, such an perspective of the Irregularity-Aware Graph Fourier Transform, approach produces dense graphs, even if variables are weakly with the goal of learning the graph signal space inner correlated (see Sec. 4 and [11]) because the modified objective product to better model data. We propose a novel method to function encourages well connected graphs [9]. This issue learn a graph with smaller edge weight upper bounds compared can be solved by incorporating non-convex sparse regularization to combinatorial Laplacian approaches. Experimentally, [11, 13] at the expense of a more complex graph our approach yields much sparser graphs compared to a learning algorithm.