Chendi Qian

Theaterstraße 35-39

52062 Aachen

Germany

I study graph machine learning, with an interest in its theoretical foundations and practical applications. I am a Ph.D. student at RWTH Aachen University, supervised by Prof. Dr. Christopher Morris.

Previously, I earned my M.Sc. at the Technical University of Munich, advised by Prof. Dr. Stephan Günnemann, and my B.Eng. at Zhejiang University, where my thesis was supervised by Prof. Dr. Ronghao Zheng.

Recent highlights

2026

Our paper Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks was accepted at NeurIPS 2026.
April 2026

Awarded Gold Reviewer at ICML 2026.

Selected publications

All publications

Solving Max-Cut to Global Optimality via Feasibility-Preserving Graph Neural Networks

Hao Chen*, Chendi Qian*, Christopher Morris, Andrea Lodi, and Can Li

Advances in Neural Information Processing Systems, 2026

HTML
On the Expressive Power of GNNs to Solve Linear SDPs

Chendi Qian, and Christopher Morris

Forty-Third International Conference on Machine Learning, 2026

HTML
Principled data augmentation for learning to solve quadratic programming problems

Chendi Qian, and Christopher Morris

Advances in Neural Information Processing Systems, 2025

Spotlight

HTML PDF
Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems

Chendi Qian, Didier Chételat, and Christopher Morris

In Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, 2024

HTML PDF

Influence-based mini-batching for graph neural networks

Johannes Gasteiger*, Chendi Qian*, and Stephan Günnemann

In Learning on Graphs Conference, 2022

Oral presentation

Bib HTML

@inproceedings{gasteiger2022influence,
  title = {Influence-based mini-batching for graph neural networks},
  author = {Gasteiger*, Johannes and Qian*, Chendi and G{\"u}nnemann, Stephan},
  booktitle = {Learning on Graphs Conference},
  pages = {9--1},
  year = {2022},
  organization = {PMLR},
  note = {<span style="color:red;">Oral presentation</span>},
  annotation = {* Equal contribution}
}