Distributable Consistent Multi-Graph Matching

In this paper we propose an optimization-based framework to multiple graph matching. The framework takes as input maps computed between pairs of graphs, and outputs maps that 1) are consistent among all pairs of graphs, and 2) preserve edge connectivity between pairs of graphs. We show how to formulate this as solving a piece-wise low-rank matrix recovery problem using a generalized message passing scheme. We also present necessary and sufficient conditions under which such global consistency is guaranteed. The key feature of our approach is that it is scalable to large datasets, while still produce maps whose quality is competent against stateof-the-art global optimization-based techniques.