Joint Graph and Vertex Importance Learning
This work addresses graph modeling for data analysis, offering incremental improvements in sparsity and interpretability.
The paper tackles the problem of graph learning by proposing a method based on the Irregularity-Aware Graph Fourier Transform to learn graph signal space inner products, resulting in sparser graphs with smaller edge weight upper bounds compared to combinatorial Laplacian approaches.
In this paper, we explore the topic of graph learning from the perspective of the Irregularity-Aware Graph Fourier Transform, with the goal of learning the graph signal space inner product to better model data. We propose a novel method to learn a graph with smaller edge weight upper bounds compared to combinatorial Laplacian approaches. Experimentally, our approach yields much sparser graphs compared to a combinatorial Laplacian approach, with a more interpretable model.