About

Hi! My name is Xiaowei Qian. I am currently a visiting student at Westlake University, working with Prof. Tailin Wu at AI for Scientific Simulation and Discovery Lab. Before this, I received my B. Eng. degree at the University of Electronic Science and Technology of China (UESTC), supervised by Prof. Zhao Kang.

āœØ Iā€™m actively applying for a Ph.D. position in 2025 Fall! Here is my CV.

šŸ” Research

My research interest currently focuses on:

  • Trustworthy Graph Learning and LLM
  • AI for Science (e.g.: dynamic system)
  • Self-supervised Graph Learning

šŸ“ Publications

* Equal Contribution

sym

A PROBABILISTIC GENERATIVE METHOD FOR SAFE PHYSICAL SYSTEM CONTROL PROBLEMS

Peiyan Hu*, Xiaowei Qian*, Wenhao Deng, Rui Wang, Haodong Feng, Ruiqi Feng, Tao Zhang, Long Wei, Yue Wang, Zhi-Ming Ma, Tailin Wu

NeurIPS Workshop on Safe Generative AI, 2024

[Paper]

TL;DR: To solve safe PDE control problems, we propose Safe Conformal Physical system control (SafeConPhy), which iteratively improves model safety with a provable safety bound.

sym

Addressing Shortcomings in Fair Graph Learning Datasets: Towards a New Benchmark

Xiaowei Qian*, Zhimeng Guo*, Jialiang Li, Haitao Mao, Bingheng Li, Suhang Wang, Yao Ma

Conference on Knowledge Discovery and Data Mining (KDD), 2024

[Paper] [Code]

TL;DR: We proposed synthetic and semi-synthetic datasets with customizable bias and constructed two more meaningful real-world datasets from Twitter to address shortcomings in existing fair graph datasets.

sym

Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clustering

Xiaowei Qian*, Bingheng Li*, Zhao Kang

Annual AAAI Conference on Artificial Intelligence (AAAI), 2024

[Paper] [Code]

TL;DR: Aimed to alleviate representation collapse in unsupervised learning, we designed a filter that upper bounding Barlow Twins to facilitate the optimization of the loss function.

šŸ“– Educations

  • 2020.09 - 2024.06, B. Eng. Degree in Computer Science, University of Electronic Science and Technology of China (UESTC).

šŸ’» Experiences