Tinglin Huang

I am a second-year Ph.D. student at Yale University, advised by Prof. Rex Ying.

Previously, I worked with Prof. Jie Tang from Tsinghua University, and Prof. Tat-Seng Chua from National University of Singapore.

My research interests revolve around computational biology, including macromolecule modeling and geometric deep learning on 3D molecular structure.

   

profile photo
Publications (* denotes equal contribution)
lft Does Negative Sampling Matter? A Review with Insights into its Theory and Applications
Zhen Yang, Ming Ding, Tinglin Huang, Yukuo Cen, Junshuai Song, Bin Xu, Yuxiao Dong, Jie Tang
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024  
PDF

An extensive review of the landscape of negative sampling techniques across different domains.

lft FAFormer: Frame Averaging Transformer for Predicting Nucleic Acid-Protein Interactions
Tinglin Huang, Zhenqiao Song, Rex Ying, Wengong Jin
MLSB Workshop, NeurIPS, 2023  
PDF

Propose an equivariant transformer architecture based on frame averaging and two nucleic aicd-proten complex (DNA/RNA-protein) datasets.

lft Learning to Group Auxiliary Datasets for Molecule
Tinglin Huang, Ziniu Hu, Rex Ying
NeurIPS, 2023  
PDF / Code

A routing-based molecule dataset grouping method.

lft BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs
Zhen Yang*, Tinglin Huang*, Ming Ding*, Yuxiao Dong, Rex Ying, Yukuo Cen, Yangliao Geng, Jie Tang
KDD, 2023  
PDF / Code

A global negative sampling method for contrastive learning.

lft GRAND+: Scalable Graph Random Neural Networks
Wenzheng Feng, Yuxiao Dong, Tinglin Huang, Ziqi Yin, Xu Cheng, Evgeny Kharlamov, Jie Tang
WWW, 2022  
PDF / Code

A scalable GNN framework for semi-supervised graph learning.

r2s MixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems
Tinglin Huang, Yuxiao Dong, Ming Ding, Zhen Yang, Wenzheng Feng, Xinyu Wang, Jie Tang
KDD, 2021  
PDF / Code

A general negative sampling plugin for GNN-based recommender systems.

umt Learning Intents behind Interactions with Knowledge Graph for Recommendation
Xiang Wang*, Tinglin Huang*, Dingxian Wang, Yancheng Yuan, Zhenguang Liu, Xiangnan He, Tat-Seng Chua
WWW, 2021  
PDF / Code

We proposed KGIN which (1) uncovers useritem relationships at the granularity of intents, and (2) applies relational path-aware aggregation.


Last updated February 2024.
Template from Jon Barron.