Signal propagation in complex networks
Signal propagation in complex networks drives epidemics, is responsible for information
going viral, promotes trust and facilitates moral behavior in social groups, enables the …
going viral, promotes trust and facilitates moral behavior in social groups, enables the …
Drew: Dynamically rewired message passing with delay
Message passing neural networks (MPNNs) have been shown to suffer from the
phenomenon of over-squashing that causes poor performance for tasks relying on long …
phenomenon of over-squashing that causes poor performance for tasks relying on long …
Reduced-order modeling
In recent years, reduced-order modeling techniques have proven to be powerful tools for
various problems in circuit simulation. For example, today, reduction techniques are …
various problems in circuit simulation. For example, today, reduction techniques are …
Neural laplace: Learning diverse classes of differential equations in the laplace domain
Abstract Neural Ordinary Differential Equations model dynamical systems with ODEs
learned by neural networks. However, ODEs are fundamentally inadequate to model …
learned by neural networks. However, ODEs are fundamentally inadequate to model …
Learning Hamiltonian neural Koopman operator and simultaneously sustaining and discovering conservation laws
Accurately finding and predicting dynamics based on the observational data with noise
perturbations is of paramount significance but still a major challenge presently. Here, for the …
perturbations is of paramount significance but still a major challenge presently. Here, for the …
Learn from one and predict all: single trajectory learning for time delay systems
This paper focuses on learning the dynamics of time delay systems from trajectory data and
proposes the use of the maximal Lyapunov exponent (MLE) as an indicator to describe the …
proposes the use of the maximal Lyapunov exponent (MLE) as an indicator to describe the …
Beyond predictions in neural ODEs: identification and interventions
H Aliee, FJ Theis, N Kilbertus - arXiv preprint arXiv:2106.12430, 2021 - arxiv.org
Spurred by tremendous success in pattern matching and prediction tasks, researchers
increasingly resort to machine learning to aid original scientific discovery. Given large …
increasingly resort to machine learning to aid original scientific discovery. Given large …
Leveraging neural differential equations and adaptive delayed feedback to detect unstable periodic orbits based on irregularly sampled time series
Detecting unstable periodic orbits (UPOs) based solely on time series is an essential data-
driven problem, attracting a great deal of attention and arousing numerous efforts, in …
driven problem, attracting a great deal of attention and arousing numerous efforts, in …
Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equations
Traffic flow forecasting is a fundamental research issue for transportation planning and
management, which serves as a canonical and typical example of spatial-temporal …
management, which serves as a canonical and typical example of spatial-temporal …
Stateful ODE-nets using basis function expansions
A Queiruga, NB Erichson… - Advances in …, 2021 - proceedings.neurips.cc
The recently-introduced class of ordinary differential equation networks (ODE-Nets)
establishes a fruitful connection between deep learning and dynamical systems. In this work …
establishes a fruitful connection between deep learning and dynamical systems. In this work …