DeepAI AI Chat
Log In Sign Up

ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equations

05/31/2021
by   Sheo Yon Jhin, et al.
0

Neural ordinary differential equations (NODEs) presented a new paradigm to construct (continuous-time) neural networks. While showing several good characteristics in terms of the number of parameters and the flexibility in constructing neural networks, they also have a couple of well-known limitations: i) theoretically NODEs learn homeomorphic mapping functions only, and ii) sometimes NODEs show numerical instability in solving integral problems. To handle this, many enhancements have been proposed. To our knowledge, however, integrating attention into NODEs has been overlooked for a while. To this end, we present a novel method of attentive dual co-evolving NODE (ACE-NODE): one main NODE for a downstream machine learning task and the other for providing attention to the main NODE. Our ACE-NODE supports both pairwise and elementwise attention. In our experiments, our method outperforms existing NODE-based and non-NODE-based baselines in almost all cases by non-trivial margins.

READ FULL TEXT

page 1

page 2

page 3

page 4

09/04/2021

Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting

Neural networks inspired by differential equations have proliferated for...
11/25/2021

Characteristic Neural Ordinary Differential Equations

We propose Characteristic Neural Ordinary Differential Equations (C-NODE...
10/12/2019

On Robustness of Neural Ordinary Differential Equations

Neural ordinary differential equations (ODEs) have been attracting incre...
11/11/2021

Climate Modeling with Neural Diffusion Equations

Owing to the remarkable development of deep learning technology, there h...
05/31/2021

OCT-GAN: Neural ODE-based Conditional Tabular GANs

Synthesizing tabular data is attracting much attention these days for va...
02/28/2022

Neural Ordinary Differential Equations for Nonlinear System Identification

Neural ordinary differential equations (NODE) have been recently propose...
12/04/2020

Universal Approximation Property of Neural Ordinary Differential Equations

Neural ordinary differential equations (NODEs) is an invertible neural n...