A General Deep Learning Framework for Network Reconstruction and Dynamics Learning
This work addresses a critical challenge in fields like biology and epidemics by enabling model-free, data-driven reconstruction of networks and dynamics, though it appears incremental as it builds on existing deep learning techniques.
The authors tackled the problem of recovering latent network structure and dynamics from observed time-series data, introducing the Gumbel Graph Network (GGN) framework, which accurately recovers network structure and predicts future states across continuous, discrete, and binary dynamics, outperforming competing methods.
Many complex processes can be viewed as dynamical systems on networks. However, in real cases, only the performances of the system are known, the network structure and the dynamical rules are not observed. Therefore, recovering latent network structure and dynamics from observed time series data are important tasks because it may help us to open the black box, and even to build up the model of a complex system automatically. Although this problem hosts a wealth of potential applications in biology, earth science, and epidemics etc., conventional methods have limitations. In this work, we introduce a new framework, Gumbel Graph Network (GGN), which is a model-free, data-driven deep learning framework to accomplish the reconstruction of both network connections and the dynamics on it. Our model consists of two jointly trained parts: a network generator that generating a discrete network with the Gumbel Softmax technique; and a dynamics learner that utilizing the generated network and one-step trajectory value to predict the states in future steps. We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods.