No abstract

Developing a tailor-made centrality measure for a given task requires domain- and network-analysis expertise, as well as time and effort. Thus, automatically learning arbitrary centrality measures for providing ground-truth node scores is an important research direction. We propose a generic deep-learning architecture for centrality learning which relies on two insights: 1. Arbitrary centrality measures can be computed using Routing Betweenness Centrality (RBC); 2. As suggested by spectral graph theory, the sound emitted by nodes within the resonating chamber formed by a graph represents both the structure of the graph and the location of the nodes. Based on these insights and our new differentiable implementation of Routing Betweenness Centrality (RBC), we learn routing policies that approximate arbitrary centrality measures on various network topologies. Results show that the proposed architecture can learn multiple types of centrality indices more accurately than the state of the art.