Almost periodic functions serve as a powerful conceptual framework in analysing differential equations whose coefficients or forcing terms exhibit recurrent behaviour over time. Rooted in the ...

Delay differential equations (DDEs) extend the classical framework of differential equations by incorporating terms that depend on past states, thus capturing the intrinsic time delays found in many ...

Building on Graph Neural Controlled Differential Equations, this repository introduces Permutation Equivariant Graph Neural CDEs, which project Graph Neural CDEs onto permutation equivariant function ...

Abstract: Neural operators, such as graph neural operators (GNOs) and Fourier neural operators (FNOs), directly learn the mapping from any functional parametric dependence to the solution and have ...

Abstract: Multivariate time series anomaly detection (MTSAD) plays a critical role in the Internet of Things (IoT) by identifying malfunctions and attacks. Graph Neural Networks (GNNs) have been ...