Fast and adaptive dynamics-on-graphs to dynamics-of-graphs translation

Lei Zhang, Zhiqian Chen, Chang-Tien Lu, Liang Zhao

Abstract: p>Numerous networks in the real world change with time, producing dynamic graphs such as human mobility networks and brain networks. Typically, the “dynamics <bold>on</bold> graphs” (e.g., changing node attribute values) are visible, and they may be connected to and suggestive of the “dynamics <bold>of</bold> graphs” (e.g., evolution of the graph topology). Due to two fundamental obstacles, modeling and mapping between them have not been thoroughly explored: (1) the difficulty of developing a highly adaptable model without solid hypotheses and (2) the ineffectiveness and slowness of processing data with varying granularity. To solve these issues, we offer a novel scalable deep echo-state graph dynamics encoder for networks with significant temporal duration and dimensions. A novel neural architecture search (NAS) technique is then proposed and tailored for the deep echo-state encoder to ensure strong learnability. Extensive experiments on synthetic and actual application data illustrate the proposed method's exceptional effectiveness and efficiency.</p>