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
Deep Manifold Computing and Visualization Using Elastic Locally Isometric Smoothness
Stan Z. Li,Zelin Zang,Lirong Wu +2 more
TL;DR: A novel method, called elastic locally isometric smoothness (ELIS), to empower deep neural networks with such an ability to preserve local geometry of highly nonlinear manifolds in high dimensional spaces and properly unfold them into lower dimensional hyperplanes is proposed.
Journal ArticleDOI
Deep manifold embedding of attributed graphs
TL;DR: Deep Manifold Embedding of Attribution Graphs (DMEAG) as mentioned in this paper proposes a loss function based on Bergman divergence to minimize the difference between embedding and structure/features.
Journal ArticleDOI
MotifRetro: Exploring the Combinability-Consistency Trade-offs in retrosynthesis via Dynamic Motif Editing
TL;DR: MotifRetro as discussed by the authors is a dynamic motif editing framework for graph-based retrosynthesis prediction that can explore the entire trade-off space and unify graphbased models.
Journal ArticleDOI
Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation
TL;DR: This paper proposes a novel multi-teacher knowledge distillation framework for Automated Graph Self-Supervised Learning ( AGSSL), which consists of two main branches: Knowledge Extraction and Knowledge Integration.
Book ChapterDOI
Invertible Manifold Learning for Dimension Reduction
TL;DR: Li et al. as mentioned in this paper proposed a two-stage dimension reduction method, called invertible manifold learning (inv-ML), to preserve the topological and geometric properties of data manifolds, which involve exactly the entire information of the data manifold.