Yuanqi Du

Yuanqi Du received Bachelor’s degree in Computer Science from George Mason University in 2021. He has broad interests in machine learning and data mining. Previously, he worked on Outlier Detection, American Sign Language Recognition (Milimeter Wave Signals & Kinect), Medical Image Analysis, Protein Structure Prediction, Molecule Generation, Deep Generative Model, and Deep Graph Learning. He worked with Dr. Liang Zhao, Dr. Amarda Shehu, Dr. Parth Pathak, Dr. Carlotta Domeniconi while he was at GMU. He worked with Dr. Hu Han and Dr. S. Kevin Zhou on Medical Image Analysis in the MIRACLE Lab at Chinese Academy of Sciences. He worked with Dr. Jianwei Zhu on Protein Structure Prediction at Microsoft Research Asia Machine Learning and Computational Biology group. He holds visiting positions at UvA AMLAB with Dr. Max Welling, CUHK MMLab with Dr. Bolei Zhou, and Dr. Adji Bousso Dieng at Princeton University. He is now a researcher under supervision of Dr. Linfeng Zhang at DP Technology. He has published several papers in top Machine Learning conferences, such as NeurIPS, ICLR, KDD, AAAI, etc. Besides Machine Learning, he is very fasinated by Sciences and very intrerested in developing ML tools for scentific problems, especially new knowledge discovery. He is actively collaborateing with researchers in chemistry, biology, physics, machine learning and data mining.

Drop me an email if you’d like to talk about/collaborate on any of the following research topics with me.

I am open to opportunities in paper review, tutorial, workshop organization in data mining, machine learning, bioinformatics, computational chemistry related topics (especially deep generative models, graph neural networks and AI for sciences).

Check out my CV and a pdf version.

Research Interests

  • Deep Graph Learning
  • Deep Generative Model
  • AI for Science (Biology/Chemistry/Physics/etc)
  • Human-centric Machine Learning
  • Machine Learning for Discovery


  • 12/21 Paper titled “Disentangled Spatiotemporal Graph Generative Model” has been accepted in AAAI 2022.
  • 11/21 Two papers titled “Interpreting Molecular Space with Deep Generative Models” (oral) and “Interpretable Molecular Graph Generation via Monotonic Constraints” have been accepted in ELLIS ML4Molecules Workshop 2021.
  • 11/21 Paper titled “Generating Tertiary Protein Structures via Interpretable Graph Variational Autoencoders” has been accepted in Bioinformatics Advances.
  • 10/21 Paper titled “Deep Latent-Variable Models for Controllable Molecule Generation” has been accepted in BIBM 2021.
  • 10/21GraphGT, the first Machine Learning Datasets for Graph Generation and Transformation, has been accepted in NeurIPS 2021. GraphGT has an easy-to-use Python API and a graph generation literature and resource collection. Please Star if you find helpful!
  • 9/21 We are organizing the seventh Deep Learning on Graphs workshop with AAAI 2022, welcome to submit your work!
  • 7/21 I am proud to announce that the first AI for Science workshop will be held with NeurIPS 2021. We focus on the gaps that stifle advacenment of AI for Science this year. We invite a list of poineers in AI for Science for great talks and panels. We also introduce very exciting Attention Track, Mentorship, and Award programs. Welcome to submit your work and join us in December! Follow us on Twitter.
  • 5/21 I will be visiting University of Amsterdam, working with Dr. Max Welling starting June 2021!!!
  • 5/21 I will join CUHK as a research intern, working with Dr. Bolei Zhou starting June 2021!!!
  • 5/21 After spending six wonderful months at MSRA, I receive a Star of Tomorrow Award!
  • 5/21 Paper titled “Deep Generative Model for Spatial Networks”, Xiaojie Guo*, Yuanqi Du*, Liang Zhao, is accpeted in KDD 2021, welcome to follow our work!!!
  • 1/21 Paper titled “Property Controllable Variational Autoencoder via Invertible Mutual Dependence”, Xiaojie Guo, Yuanqi Du, Liang Zhao*, accepted in ICLR 2021.
  • 12/20 Paper titled “Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models” is accepted in IPCAI 2021 and will be published in IJCARS.