1 citations · 1 across the 5 of their papers we have counts for
5 papers
Lyapunov Stable Graph Neural Flow
Haoyu Chu, Xiaotong Chen, Wei Zhou +4
Graph Neural Networks (GNNs) are highly vulnerable to adversarial perturbations in both topology and features, making the learning of robust representations a critical challenge. I…
Structure-Preserving Physics-Informed Neural Networks With Energy or Lyapunov Structure
Haoyu Chu, Yuto Miyatake, Wenjun Cui +2
Recently, there has been growing interest in using physics-informed neural networks (PINNs) to solve differential equations. However, the preservation of structure, such as energy…
Lyapunov-Stable Deep Equilibrium Models
Haoyu Chu, Shikui Wei, Ting Liu +2
Deep equilibrium (DEQ) models have emerged as a promising class of implicit layer models, which abandon traditional depth by solving for the fixed points of a single nonlinear laye…
Improving Neural ODEs via Knowledge Distillation
Haoyu Chu, Shikui Wei, Qiming Lu +1
Neural Ordinary Differential Equations (Neural ODEs) construct the continuous dynamics of hidden units using ordinary differential equations specified by a neural network, demonstr…
Towards Natural Robustness Against Adversarial Examples
Haoyu Chu, Shikui Wei, Yao Zhao
Recent studies have shown that deep neural networks are vulnerable to adversarial examples, but most of the methods proposed to defense adversarial examples cannot solve this probl…