S
Stan Z. Li
Researcher at Westlake University
Publications - 625
Citations - 49737
Stan Z. Li is an academic researcher from Westlake University. The author has contributed to research in topics: Facial recognition system & Computer science. The author has an hindex of 97, co-authored 532 publications receiving 41793 citations. Previous affiliations of Stan Z. Li include Microsoft & Macau University of Science and Technology.
Papers
More filters
Discovering and Explaining the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions
TL;DR: In this article , the authors explore the capacity of GNNs to capture interactions between nodes under contexts with different complexities and propose a novel graph rewiring approach based on interaction patterns learned by GNN to adjust the receptive nodes of each node dynamically.
RFold: RNA Secondary Structure Prediction with Decoupled Optimization
Cheng Tan,Zhan Gao,Stan Z. Li +2 more
TL;DR: RFold as discussed by the authors decomposes the vanilla constraint satisfaction problem into row-wise and column-wise optimization, simplifying the solving process while guaranteeing the validity of the output, and adopts attention maps as informative representations instead of designing hand-crafted features.
Journal ArticleDOI
Precipitation estimation based on infrared data with a spherical convolutional neural network
TL;DR: In this article , a deep learning model using a spherical convolutional neural network (PEISCNN) was constructed to properly represent the Earth's spherical surface, which showed significant improvement in the metrics of POD, CSI, RMSE and CC, especially in the dry region and for extreme rainfall events.
Proceedings ArticleDOI
Deep Manifold Graph Auto-Encoder For Attributed Graph Embedding
TL;DR: In this paper , a Deep Manifold (Variational) Graph Auto-Encoder (DMVGAE/DMGAE) was proposed to improve the stability and quality of learned representations to tackle the crowding problem.
Journal ArticleDOI
InstructBio: A Large-scale Semi-supervised Learning Paradigm for Biochemical Problems
TL;DR: In this paper , the authors proposed InstructMol, a semi-supervised learning algorithm to take better advantage of unlabeled examples, which introduces an instructor model to provide the confidence ratios as the measurement of pseudo-labels' reliability.