DeepAI AI Chat
Log In Sign Up

Neural Dynamics on Complex Networks

by   Chengxi Zang, et al.

We introduce a deep learning model to learn continuous-time dynamics on complex networks and infer the semantic labels of nodes in the network at terminal time. We formulate the problem as an optimal control problem by minimizing a loss function consisting of a running loss of network dynamics, a terminal loss of nodes' labels, and a neural-differential-equation-system constraint. We solve the problem by a differential deep learning framework: as for the forward process of the system, rather than forwarding through a discrete number of hidden layers, we integrate the ordinary differential equation systems on graphs over continuous time; as for the backward learning process, we learn the optimal control parameters by back-propagation during solving initial value problem. We validate our model by learning complex dynamics on various real-world complex networks, and then apply our model to graph semi-supervised classification tasks. The promising experimental results demonstrate our model's capability of jointly capturing the structure, dynamics and semantics of complex systems.


page 20

page 21

page 22

page 23


Deep learning as optimal control problems: models and numerical methods

We consider recent work of Haber and Ruthotto 2017 and Chang et al. 2018...

Time-Reversal Symmetric ODE Network

Time-reversal symmetry, which requires that the dynamics of a system sho...

Sparse approximation in learning via neural ODEs

We consider the continuous-time, neural ordinary differential equation (...

Neural ODEs with stochastic vector field mixtures

It was recently shown that neural ordinary differential equation models ...

A Shooting Formulation of Deep Learning

Continuous-depth neural networks can be viewed as deep limits of discret...

Control On the Manifolds Of Mappings As a Setting For Deep Learning

We use a control-theoretic setting to model the process of training (dee...

Improving deep learning precipitation nowcasting by using prior knowledge

Deep learning methods dominate short-term high-resolution precipitation ...