121 citations · 295 across the 14 of their papers we have counts for
14 papers
Power-law Dynamic arising from machine learning
Wei Chen, Weitao Du, Zhi-Ming Ma +1
We study a kind of new SDE that was arisen from the research on optimization in machine learning, we call it power-law dynamic because its stationary distribution cannot have sub-G…
Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
Shengchao Liu, Weitao Du, Yanjing Li +10
Artificial intelligence for scientific discovery has recently generated significant interest within the machine learning and scientific communities, particularly in the domains of…
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
Shengchao Liu, Weitao Du, Zhiming Ma +2
Molecule pretraining has quickly become the go-to schema to boost the performance of AI-based drug discovery. Naturally, molecules can be represented as 2D topological graphs or 3D…
A new perspective on building efficient and expressive 3D equivariant graph neural networks
Weitao Du, Yuanqi Du, Limei Wang +5
Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a co…
Structure-based Drug Design with Equivariant Diffusion Models
Arne Schneuing, Charles Harris, Yuanqi Du +10
Structure-based drug design (SBDD) aims to design small-molecule ligands that bind with high affinity and specificity to pre-determined protein targets. Generative SBDD methods lev…
A Flexible Diffusion Model
Weitao Du, Tao Yang, He Zhang +1
Diffusion (score-based) generative models have been widely used for modeling various types of complex data, including images, audios, and point clouds. Recently, the deep connectio…
An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
Shiqi Gong, Qi Meng, Jue Zhang +6
Deep learning methods have been increasingly adopted to study jets in particle physics. Since symmetry-preserving behavior has been shown to be an important factor for improving th…
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
Weitao Du, He Zhang, Yuanqi Du +4
Group equivariance (e.g. SE(3) equivariance) is a critical physical symmetry in science, from classical and quantum physics to computational biology. It enables robust and accurate…
Reflecting brownian motion and the gauss-bonnet-chern theorem
Weitao Du, Elton P. Hsu
We use reflecting Brownian motion (RBM) to prove the well known Gauss-Bonnet-Chern theorem for a compact Riemannian manifold with boundary. The boundary integrand is obtained by ca…
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
Wei Huang, Yayong Li, Weitao Du +4
Graph convolutional networks (GCNs) and their variants have achieved great success in dealing with graph-structured data. Nevertheless, it is well known that deep GCNs suffer from…
Implicit bias of deep linear networks in the large learning rate phase
Wei Huang, Weitao Du, Richard Yi Da Xu +1
Most theoretical studies explaining the regularization effect in deep learning have only focused on gradient descent with a sufficient small learning rate or even gradient flow (in…
Constructing exchangeable pairs by diffusion on manifolds and its application
Weitao Du
We construct a continuous family of exchangeable pairs by perturbing the random variable through diffusion processes on manifold in order to apply Stein method to certain geometric…
On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization
Wei Huang, Weitao Du, Richard Yi Da Xu
The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training. The increase in learning speed that results from orthogonal…
Mean field theory for deep dropout networks: digging up gradient backpropagation deeply
Wei Huang, Richard Yi Da Xu, Weitao Du +2
In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success. The theory has been applied to various neural netw…