Search Results for author: Stan. Z Li

Found 4 papers, 2 papers with code

DMT-HI: MOE-based Hyperbolic Interpretable Deep Manifold Transformation for Unspervised Dimensionality Reduction

no code implementations25 Oct 2024 Zelin Zang, Yuhao Wang, Jinlin Wu, Hong Liu, Yue Shen, Stan. Z Li, Zhen Lei

DMT-HI enhances DR accuracy by leveraging hyperbolic embeddings to represent the hierarchical nature of data, while also improving interpretability by explicitly linking input data, embedding outcomes, and key features through the MOE structure.

Dimensionality Reduction

DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation

1 code implementation10 Sep 2023 Zelin Zang, Hao Luo, Kai Wang, Panpan Zhang, Fan Wang, Stan. Z Li, Yang You

With the help of iterative training of the semantic encoder and diffusion model, DiffAug improves the representation ability in an uninterrupted and unsupervised manner.

Contrastive Learning Data Augmentation +2

Git: Clustering Based on Graph of Intensity Topology

4 code implementations4 Oct 2021 Zhangyang Gao, Haitao Lin, Cheng Tan, Lirong Wu, Stan. Z Li

\textbf{A}ccuracy, \textbf{R}obustness to noises and scales, \textbf{I}nterpretability, \textbf{S}peed, and \textbf{E}asy to use (ARISE) are crucial requirements of a good clustering algorithm.

Clustering Clustering Algorithms Evaluation

LookHops: light multi-order convolution and pooling for graph classification

no code implementations28 Dec 2020 Zhangyang Gao, Haitao Lin, Stan. Z Li

Convolution and pooling are the key operations to learn hierarchical representation for graph classification, where more expressive $k$-order($k>1$) method requires more computation cost, limiting the further applications.

General Classification Graph Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.