Graph matching by graph neural network
Xiyang Liu · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign) · 2018
Graph matching or network alignment refers to the problem of matching two correlated graphs. This thesis presents a deep Q learning based method, which represents the matching process by a graph neural network. By breaking the symmetry, the parameterized graph neural network is able to capture a wide range of neighborhoods. Extensive experiments on various training and testing data have shown better performance, strong scalability and the ability to adapt to different domains.