Xitong Zhang

Xitong Zhang

Ph.D. candidate in Computational Mathematics

Michigan State University

Biography

I’m Xitong Zhang, currently pursuing my Ph.D. in Computational Mathematics at Michigan State University. I’m honored to be under the guidance of Dr. Wang, Rongrong and Dr. Hirn, Matthew. My academic journey has been deeply rooted in the study of machine learning and its wide-ranging applications. My research interests are broad, covering topics from the generalization theory to the graph neural networks. Moreover, I’ve also explored the realm of geophysics, with a particular emphasis on data-driven frameworks for seismic data analysis.

Interests
  • Learning on Graphs
  • AI for Science
  • Generalization
Education
  • Ph.D. candidate in Computational Mathematics

    Michigan State University, United States

  • MSc in Computer Science

    Michigan State University, United States, 2020

  • MSc in Computer Science

    Worcester Polytechnic Institute, United States, 2018

  • BEng in Artificial Intelligence

    Hunan University, China, 2016

Experience

 
 
 
 
 
Michigan State University
Graduate Research/Teching Assistant
Michigan State University
August 2018 – Present Michigan, United States
Machine learning Theory and the applications on Directed Graph Neural Networks, Spatiotemporal Data Mining, Generalization and Regularization.
 
 
 
 
 
Qualcomm
Machine Learning Engineer Intern
May 2023 – August 2023 California, United States
Supervised and Unsupervised Image Inpainting and Outpainting by Diffusion Models.
 
 
 
 
 
Los Alamos National Lab
Graduate Research Assistant
Los Alamos National Lab
March 2022 – August 2022 New Mexico, United States
Generated large-scale datasets and Uncertainty Quantification for end-to-end Data-driven Full Waveform Inversion (FWI).
 
 
 
 
 
Los Alamos National Lab
Graduate Research Assistant
Los Alamos National Lab
June 2021 – August 2021 New Mexico, United States
Physics-informed Machine Learning for Full Waveform Inversion (FWI).
 
 
 
 
 
Los Alamos National Lab
Graduate Research Assistant
Los Alamos National Lab
June 2020 – August 2020 New Mexico, United States
GNN-based Earthquake Characterization; Squential Seismic Images Generation.
 
 
 
 
 
Worcester Polytechnic Institute
Graduate Research Assistant
Worcester Polytechnic Institute
October 2017 – May 2018 Massachusetts, United States
Image Segmentation on Live cell Images.

Projects

*
Inpainting and Outpainting with Diffusion Models
During the Qualcomm 2023 summer internship, we initially delved into unsupervised inpainting and outpainting using the RePaint framework. We enhanced this by introducing a smoothing guidance for improved sampling. To speed up the diffusion process, we then investigated both unsupervised and supervised Wavelet Diffusion Models.
OpenFWI Datasets
OpenFWI is a collection of large-scale, multi-structural benchmark datasets for machine learning driven seismic FWI. We release twelve datasets synthesized from different priors, including one 3D dataset. We also provide baseline experimental results with four deep learning methods, InversionNet, VelocityGAN, UPFWI and InversionNet3D. OpenFWI is the first open-source platform to facilitate data-driven FWI research. It will be actively developed and the datasets are expected to evolve.
PyTorch Geometric Signed Directed
PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. It builds on open-source deep-learning and graph processing libraries. PyTorch Geometric Signed Directed consists of various signed and directed geometric deep learning, embedding, and clustering methods from a variety of published research papers and selected preprints.
FeedGrain Visualization
The system is designed to visualize the US historical feed grain data and gain insights into the supply and the demand of feed grains in domestic market and international trade of the US with import and export partners.

Recent Publications

Quickly discover relevant content by filtering publications.
(2023). PAC-tuning: Fine-tuning Pre-trained Language Models with PAC-driven Perturbed Gradient Descent. EMNLP 2023.

(2023). Can Directed Graph Neural Networks be Adversarially Robust?.

PDF Cite

(2023). Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent. ICLR 2023 notable top 25%.

PDF Cite Slides

(2022). OpenFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion. NeurIPS.

PDF Cite Project

Contact