Tieliang Gong | Xi'an Jiaotong University

About Me

I am an Associate Professor at the School of Computer Science and Technology at Xi’an Jiaotong University. My students and I are part of the Shaanxi Key Lab of BDKE. Our research is funded by the National Key Research Development Program of China and the National Natural Science Foundation.

I have previously held positions as a postdoctoral researcher at the University of Ottawa and as a visiting scholar at the University of Michigan, Ann Arbor. I obtained my Ph.D in Applied Mathematics from Xi’an Jiaotong University, where I was fortunate to be advised by Prof. Zongben Xu, an esteemed Academician of the Chinese Academy of Sciences.

I am open to exploring any potential collaboration opportunities. Please let me know if you’d like to collaborate, especially if you’re interested in information theoretical learning issues.

Research

My research interests mainly include machine learning theory and information theory. My goal is to develop the foundational theory that guides the design of computationally efficient machine learning algorithms that do not cause degeneration. Recently, my research revolves around some critical challenges in big data analysis within the information theoretical learning framework, including but not limited to conducting generalization analysis for deep learning algorithms, developing novel information theoretical measures, fast approximation algorithms and corresponding statistical guarantees. Besides, I am also interested in exploring its potential applications in AI for science.

Recruiting

I am looking for highly motivated and self-driven students, who are interested in

Robust/Explainable machine learning, especially on coreset selection, subsampling, random sketching and kernel methods etc.
Generalization of DNNs, aims to open the black-box of deep learning. Theoretical investigation including complexity analysis, stability analysis, SGD/SGLD analysis etc.
Transfer learning, including out-of-distribution generalization/Detection based on information theoretical learning framework.
AI for Medical, especially on pathology image analysis, drug recommendation and related topics on XAI for Medical

People

Formal doctoral students: Zeyu Gao (Now at University of Cambridge), Kai He (Now at National University of Singapore)
Current Ph.D. students: Yuxin Dong (Co-advised by Prof. Chen Li), Wen Wen, Jialun Wu (Co-advised by Prof. Chen Li)
Current Master students: Zeyang Zhang, Haoyang Zhang, Ying Huang, Huiting Huang

Publications

ICLR

Rethinking Information-Theoretical Generalization: Loss entropy induced PAC Bounds

Yuxin Dong, Tieliang Gong*, Hong Chen, Chen Li (*Corresponding authors)

International Conference on Learning Representation, 2024.

CVPR

ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification

Jiangbo Shi, Chen Li, Tieliang Gong, Yefeng Zheng, Huazhu Fu*

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

ICLR

Learning Guarantees for Non-convex Pairwise SGD with Heavy Tails

Jun Chen, Hong Chen*, Bin Gu, Tieliang Gong, WeiFu Li

International Conference on Learning Representation, 2024.

IEEE TNNLS

Markov Subsampling Based on Huber Criterion

Tieliang Gong*, Yuxin Dong, Hong Chen, Bo Dong, Chen Li

IEEE Transactions on Neural Networks and Learning Systems, 2024.

IEEE TIT

Optimal Randomized Approximations for Matrix-based Renyi's Entropy

Yuxin Dong, Tieliang Gong*, Shujian Yu, Chen Li

IEEE Transactions on Information Theory, 2023.

IEEE TSP

Computationally Efficient Approximations for Matrix-based Renyi's Entropy

Tieliang Gong*, Yuxin Dong, Shujian Yu, Bo Dong

IEEE Transactions on Signal Processing, 2023.

ICML

Tilted Sparse Additive Models

Yingjie Wang, Hong Chen, Weifeng Liu, Tieliang Gong, Youcheng Fu, Dacheng Tao

International Conference on Machine Learning, 2023.

AAAI

Robust and Fast Measure of Information via Low-rank Representation

Yuxin Dong, Tieliang Gong*, Shujian Yu, Hong Chen, Chen Li

AAAI Conference on Artificial Intelligence, 2023.

IJCAI

Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective

Yuxin Dong, Tieliang Gong*, Hong Chen, Chen Li

International Joint Conference on Artificial Intelligence, 2023.

BioInfo

Dual Attention and Patient Similarity Network for Drug Recommendation

Jialun Wu, Yuxin Dong, Zeyu Gao, Tieliang Gong, Chen Li

Bioinformatics, 2023.

ACL

PRAM: An End-to-end Prototype-based Representation Alignment Model for Zero-resource Cross-lingual Named Entity Recognition

Yucheng Huang, Wenqiang Liu, Xianli Zhang, Jun Lang, Tieliang Gong, Chen Li

Annual Meeting of the Association for Computational Linguistics, 2023.