Constructing neural network based models for simulating dynamical systems
Dynamical systems see widespread use in natural sciences like physics, biology, and
chemistry, as well as engineering disciplines such as circuit analysis, computational fluid …
chemistry, as well as engineering disciplines such as circuit analysis, computational fluid …
On neural differential equations
P Kidger - arXiv preprint arXiv:2202.02435, 2022 - arxiv.org
The conjoining of dynamical systems and deep learning has become a topic of great
interest. In particular, neural differential equations (NDEs) demonstrate that neural networks …
interest. In particular, neural differential equations (NDEs) demonstrate that neural networks …
Neural sdes as infinite-dimensional gans
Stochastic differential equations (SDEs) are a staple of mathematical modelling of temporal
dynamics. However, a fundamental limitation has been that such models have typically been …
dynamics. However, a fundamental limitation has been that such models have typically been …
Hope: High-order graph ode for modeling interacting dynamics
Leading graph ordinary differential equation (ODE) models have offered generalized
strategies to model interacting multi-agent dynamical systems in a data-driven approach …
strategies to model interacting multi-agent dynamical systems in a data-driven approach …
Improving social network embedding via new second-order continuous graph neural networks
Graph neural networks (GNN) are powerful tools in many web research problems. However,
existing GNNs are not fully suitable for many real-world web applications. For example, over …
existing GNNs are not fully suitable for many real-world web applications. For example, over …
[PDF][PDF] GRAND++: Graph neural diffusion with a source term
ABSTRACT We propose GRAph Neural Diffusion with a source term (GRAND++) for graph
deep learning with a limited number of labeled nodes, ie, low-labeling rate. GRAND++ is a …
deep learning with a limited number of labeled nodes, ie, low-labeling rate. GRAND++ is a …
Neural flows: Efficient alternative to neural ODEs
Neural ordinary differential equations describe how values change in time. This is the
reason why they gained importance in modeling sequential data, especially when the …
reason why they gained importance in modeling sequential data, especially when the …
Heavy ball neural ordinary differential equations
We propose heavy ball neural ordinary differential equations (HBNODEs), leveraging the
continuous limit of the classical momentum accelerated gradient descent, to improve neural …
continuous limit of the classical momentum accelerated gradient descent, to improve neural …
SE (3) equivariant graph neural networks with complete local frames
Abstract Group equivariance (eg SE (3) equivariance) is a critical physical symmetry in
science, from classical and quantum physics to computational biology. It enables robust and …
science, from classical and quantum physics to computational biology. It enables robust and …
Steer: Simple temporal regularization for neural ode
Abstract Training Neural Ordinary Differential Equations (ODEs) is often computationally
expensive. Indeed, computing the forward pass of such models involves solving an ODE …
expensive. Indeed, computing the forward pass of such models involves solving an ODE …