Jingtun Zhang [张劲暾]

Master Student, Texas A&M University



Howdy! I am currently a 1st year Master student (MCS) in the Department of Computer Science & Engineering, Texas A&M University. My advisor is Prof. Shuiwang Ji, who leads the Data Integration, Visualization, and Exploration (DIVE) Laboratory. I obtained my bachelor’s degree from the Department of Computer Science and Technology, University of Science and Technology of China in 2020.

My major focus on algorithms and machine learning. Specifically, I am familiar with (1) software building and algorithms, and (2) machine learning algorithms for graph data (Graph-Neural-Network).

Publications [Google Scholar]

* indicates equal contribution.

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

Meng Liu*, Youzhi Luo*, Limei Wang*, Yaochen Xie*, Hao Yuan*, Shurui Gui*, Haiyang Yu*, Zhao Xu, Jingtun Zhang, Yi Liu, Keqiang Yan, Haoran Liu, Cong Fu, Bora Oztekin, Xuan Zhang, and Shuiwang Ji

Journal of Machine Learning Research (JMLR), 2021.

Self-Supervised Learning of Graph Neural Networks: A Unified Review

Yaochen Xie, Zhao Xu, Jingtun Zhang, Zhengyang Wang, Shuiwang Ji

Preprint, 2021.


Open Catalyst Challenge (Rank #3) Link
1. Building machine learning models to simulate the relaxtion process of a molecular system.
2. Dataset preprocessing and profiling to differentiate the distribution of adsorbate and catalyst.
3. Spliting dataset by the distribution of the system to train models on different subsplits to ensemble.

Dive Into Graphs Link
1. Implementing a unified library for graph deep learning algorithms, data interface and baseline.
2. Coding for data loading, preprocessing and evaluation strategies of graph self-supervised learning part.
3. Achieved better or comparable results and computation complexity than most authors’ code.

Kayak for Mask Link
1. Course work for building a Kayak-like website for kid’s mask searching and filtering.
2. Based on Django framework and able to update information by spidering online sheets and store pages.
3. Deployed on Heroku [Link] by docker images to serve as public resource for fighting Covid-19.

Bank Database Application Link
1. Course work implemented a small full-stack bank database system as interface and management platform.
2. Building with popular framework: front end by Vuejs, back end by Flask and DBMS by Oracle.


My résumé is available here [PDF].