4 papers · 1 filter
INDEQS: Informed Neural controlled Differential EQuationS
Michael Detzel, Gabriel Nobis, Kristiyan Blagov +3
Neural Controlled Differential Equations (NCDE) provide a powerful continuous-time framework for forecasting time series, but standard graph-based extensions typically learn spatia…
Synthetic Datasets for Machine Learning on Spatio-Temporal Graphs using PDEs
Jost Arndt, Utku Isil, Michael Detzel +2
Many physical processes can be expressed through partial differential equations (PDEs). Real-world measurements of such processes are often collected at irregularly distributed poi…
Generative Fractional Diffusion Models
Gabriel Nobis, Maximilian Springenberg, Marco Aversa +11
We introduce the first continuous-time score-based generative model that leverages fractional diffusion processes for its underlying dynamics. Although diffusion models have excell…
Spatial Shortcuts in Graph Neural Controlled Differential Equations
Michael Detzel, Gabriel Nobis, Jackie Ma +1
We incorporate prior graph topology information into a Neural Controlled Differential Equation (NCDE) to predict the future states of a dynamical system defined on a graph. The inf…