Me
Chenqing (Will) Hua
CS@McGill University & Mila
chenqing.hua [at] mail.mcgill.ca
chenqing.hua [at] mila.quebec

About

Hi, I am a research master student at McGill & Mila working on geometric deep learning and generative models for molecule and protein structures. I am fortunately supervised and fully funded by Doina Precup and Guy Wolf. I received a bachelor degree in computer science (with first-class honours) at McGill & Mila, where I completed my thesis under supervision of William Hamilton on graph neural networks and heterophily. You can find my CV.

I am interested in machine learning with a focus on geometric deep learning and deep generative models for chemistry and biology. I envision a world where every disease finds a cure, and no one has to suffer from illness anymore (in 20 years).

I am looking for full-time PhD positions starting in Fall 2025! Please feel free to reach out to me for any information :)

Interests

  • Machine Learning & AI for Drug Discovery
    • Geometric Deep Learning
    • Deep Generative Models
    • Molecules and Proteins

Education

McGill University & Mila, Sep, 2022 - May, 2024
  • M.Sc in Computer Science (3.75/4.00)
McGill University & Mila, Sep, 2018 - May, 2022
  • B.Sc (First-Class Honours) in Computer Science (3.90/4.00)

News

  • Give a talk on protein-protein interaction prediction to Jian Tang's group. [Slide]
  • Give a talk on structure-based molecule design at LoG2023 Montreal. [Slide][Video]
  • One paper accepted to 2nd Learning on Graphs Conference.
  • One paper accepted to 37th Conference on Neural Information Processing Systems.
  • One paper accepted to 12th International Conference on Complex Networks and their Applications.
  • One paper accepted to 36th Conference on Neural Information Processing Systems, GLFrontiers, and selected for Oral presentation.
  • Two papers accepted to 36th Conference on Neural Information Processing Systems, and one paper selected for Spotlight presentation.

Publications

MUDiff: Unified Diffusion for Complete Molecule Generation
Hua, C., Luan, S., Xu, M., Ying, R., Fu, J., Ermon, S., Precup, D.
Learning On Graphs Conference, 2023
[ Paper]
When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability
Luan, S., Hua, C., Xu, M., Lu, Q., Zhu, J., Chang, XW., Fu, J., Leskovec, J., Precup, D.
Neural Information Processing Systems, 2023
[ Paper]
When Do We Need GNN for Node Classification?
Luan, S., Hua, C., Lu, Q., Zhu, Jia., Chang, X. W., Precup, D.
International Conference on Complex Networks and their Applications, 2023
[ Paper]
Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
Luan, S.*, Zhao, M.*, Hua, C.*, Chang, X. W., Precup, D
Neural Information Processing Systems GLFrontiers, 2022
[ Paper]
Oral Presentation
Revisiting Heterophily For Graph Neural Networks
Luan, S., Hua, C., Lu, Q., Zhu, Jia., Zhao, M., Zhang, S., Chang, X. W., Precup, D.
Neural Information Processing Systems, 2022
[ Paper]
Spotlight Presentation
High-Order Pooling for Graph Neural Networks with Tensor Decomposition
Hua, C., Rabusseau, G., Tang, J.
Neural Information Processing Systems, 2022
[ Paper]

Preprints

Effective Protein-Protein Interaction Exploration with PPIretrieval
Hua, C., Coley, C., Wolf, G., Precup, D., Zheng, S.
Preprint
[ Paper]
Graph neural networks intersect probabilistic graphical models: A survey
Hua, C., Luan, S., Zhang, Q., Fu, J.
Preprint
[ Paper]
Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
Luan, S.*, Hua, C.*, Chang, X. W., Precup, D
Preprint
[ Paper]

Selected Honors & Awards

Experiences

Sep, 2023 - Now
Research Intern @ Aureka Biotechnologies
Effective Protein-Protein Interaction Exploration with PPIretrieval
Supervisor: Shuangjia Zheng
May, 2022 - Dec, 2022
Research Intern @ Mila
GFlowNets for Molecular Conformation Generation
Supervisor: Yoshua Bengio
Jun, 2021 - Jan, 2022
Research Intern @ Mila
High-Order Pooling for Graph Neural Networks with Tensor Decomposition
Supervisor: Jian Tang and Guillaume Rabusseau
Dec, 2020 - Apr, 2021
Research Intern @ Mila
Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
Supervisor: William Hamiltom

Teaching

Teaching Assistant

Academic Services

Reviewer: ICML2022, LoG2022, NeurIPS2022 AI4Mat, NeurIPS2022 GLFrontier, ICML2023, NeurIPS2023, KDD2023 PhD Consortium, LoG2023, ICLR2024, ICLR2024 GEM, ICLR2024 AGI, ICML2024
Area Chair: NeurIPS2023 GLFrontier
Organizer: LoG2023 Montreal

Miscellaneous

🏃‍♀️ I lift weights and do cardios.
🥇 In personal ethics, I deeply respect the intrinsic value of every individual, regardless of background, race, or beliefs. My ethical principles align closely with the institute's goals, guiding my convictions. These ethics are not just words; they form the foundation of my beliefs for research. It is crucial that our AI endeavors are grounded in a strong commitment to individual rights.
Top