ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equations
arXiv:2105.14953
Abstract
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.
arXiv commentAccepted by KDD 2021
References in corpus (10)
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- Effective Approaches to Attention-based Neural Machine Translation
- Neural Ordinary Differential Equations
- Deep Kalman Filters
- How to train your neural ODE: the world of Jacobian and kinetic regularization
- Dissecting Neural ODEs
- Learning Differential Equations that are Easy to Solve
- Augmented Neural ODEs
- On Robustness of Neural Ordinary Differential Equations
- Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands