10 citations · 43 across the 15 of their papers we have counts for
13 papers · 1 filter
Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks
Woojin Cho, Kookjin Lee, Donsub Rim +1
In various engineering and applied science applications, repetitive numerical simulations of partial differential equations (PDEs) for varying input parameters are often required (…
Reversible and irreversible bracket-based dynamics for deep graph neural networks
Anthony Gruber, Kookjin Lee, Nathaniel Trask
Recent works have shown that physics-inspired architectures allow the training of deep graph neural networks (GNNs) without oversmoothing. The role of these physics is unclear, how…
Time Series Forecasting with Hypernetworks Generating Parameters in Advance
Jaehoon Lee, Chan Kim, Gyumin Lee +6
Forecasting future outcomes from recent time series data is not easy, especially when the future data are different from the past (i.e. time series are under temporal drifts). Exis…
Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting
Fan Wu, Sanghyun Hong, Donsub Rim +2
Continuous-time dynamics models, such as neural ordinary differential equations, have enabled the modeling of underlying dynamics in time-series data and accurate forecasting. Howe…
Parameter-varying neural ordinary differential equations with partition-of-unity networks
Kookjin Lee, Nathaniel Trask
In this study, we propose parameter-varying neural ordinary differential equations (NODEs) where the evolution of model parameters is represented by partition-of-unity networks (PO…
AdamNODEs: When Neural ODE Meets Adaptive Moment Estimation
Suneghyeon Cho, Sanghyun Hong, Kookjin Lee +1
Recent work by Xia et al. leveraged the continuous-limit of the classical momentum accelerated gradient descent and proposed heavy-ball neural ODEs. While this model offers computa…