B1237
Title: Clustered graph matching for label recovery and graph classification
Authors: Zhirui Li - University of Maryland College Park (United States)
Jesus Arroyo - Texas A&M University (United States)
Konstantinos Pantazis - Johns Hopkins University (United States)
Vince Lyzinski - University of Maryland, College Park (United States) [presenting]
Abstract: Given a collection of vertex-aligned networks and an additional label-shuffled network, procedures for leveraging the signal in the vertex-aligned collection are proposed to recover the labels of the shuffled network. Matching the shuffled network to averages of the networks in the vertex-aligned collection at different levels of granularity is considered. It is demonstrated in theory and practice that if the graphs come from different network classes, clustering the networks into classes followed by matching the new graph to cluster averages can yield higher fidelity matching performance than matching to the global average graph. Moreover, by minimizing the graph-matching objective function for each cluster average, this approach simultaneously classifies and recovers the vertex labels for the shuffled graph. These theoretical developments are further reinforced via an illuminating real-data experiment matching human connectomes.