Mingming Gong


Home


Mingming Gong

Mingming Gong

Senior Lecturer in Data Science, ARC DECRA Fellow
School of Mathematics and Statistics
Melbourne Centre for Data Science
The University of Melbourne

Associate Professor in Machine Learning (Affiliated)
Department of Machine Learning
Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates

Office: 111 Old Geology Building South, Parkville, VIC, Australia
E-mail: mingming.gong[at]unimelb.edu.au
[Google Scholar] [UoM Homepage] [MBZUAI Homepage]

I am a senior lecturer in Data Science at the School of Mathematics and Statistics and Melbourne Centre for Data Science, the University of Melbourne (UoM), and an affiliated associate professor of Machine Learning at Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI). I am the co-founder and co-director of UoM Causal Learning & Reasoning Group and the Melbourne Deep Learning Group. Before joining UoM, I was a postdoctoral research fellow at University of Pittsburgh and Carnegie Mellon University, working with Prof Kayhan Batmanghelich and Prof Kun Zhang. I obtained my PhD from University of Technology Sydney, supervised by Prof Dacheng Tao and co-supervised by Prof Kun Zhang, Master degree from Huazhong University of Science and Technology, and bachelor's degree from Nanjing University. From 03/2013 - 10/2013, I was a research intern at Max-Planck Institute for Intelligent Systems (Prof Bernhard Schölkopf's lab).

I am always looking for highly-motivated students with strong mathematical background and/or proficient coding skills. If you are interested in working with me, please send me an email about your interests and background (attaching your CV, transcripts, and any previous research papers). Thanks!

  • To potential PhD/MPhil students. I accept PhD/MPhil students at both UoM and MBZUAI. Feel free to contact me if you plan to do research on machine learning for your PhD's thesis. Full scholarships will be provided for talented PhD applicants.

  • To UoM Master by Coursework students. Please contact me if you plan to do research on machine learning for your Master's thesis. I supervise students from data science, statistics, and computer science. I prefer to mentor students who are genuinely committed to pursuing a research career.

  • To undergraduate students. Due to my current heavy supervisory commitments, I am unable to take on undergraduate students at this time.

  • To visiting scholar/PhD students. Please drop me an email if your research area overlaps with mine.



Research Interests

I am dedicated to providing theoretical foundations and computational innovations in understanding the generative process of real-world complex data. My research focuses on two levels of generative models. The first level involves learning from observational data distributions to sample new data. The second level involves generative models that depict the underlying causal structure of the data distribution. Causal generative models go beyond mere data generation; they enable intervention in the system by manipulating variables and observing the consequences. I aim to explore the causal generative process of data to learn causal representations that are transferable, robust, and interpretable. Additionally, I am interested in designing learning models tailored for various types of real data, including but not limited to image and video data, 3D data, time series data, biological data, and multi-modal data.

  • Causal Learning: Causal discovery & inference, Causal generative models, Causal fairness, Causal representation learning

  • Deep Learning: Deep generative model, Multi-modal learning, Transfer Learning, Weakly-supervised learning

  • Real data: Image, Video, 3D, time series, protein, DNA, etc.


Recent Updates

  • 01/2024, congrats to Erdun and Aoqi for their papers accepted to ICLR 2024. Additionally, two collaborative papers got accepted, congrats to the team!

  • 01/2024, congrats to Wenqin for her first paper accepted to CLeaR 2024.

  • 01/2024, I am honored to announce my role as the Program Co-Chair for the Australasian Conference on Artificial Intelligence 2024. I extend a warm invitation for you to attend the conference, scheduled to take place in Melbourne this November.

  • 11/2023, we are honored to receive an ARC discovery project to work on federated causal inference.

  • 09/2023, congratulations to Yuanyuan on her first NeurIPS paper! Additionally, four collaborative papers got accepted, congrats to the team!

  • 07/2023, congrats to Dongting and Ziye for their papers accepted to ICCV 2023.

  • 10/2022, congrats to Erdun for his paper on federated DAG learning accepted to TMLR.

  • 08/2022, I will serve as Area Chair for ICML 2023 and UAI 2023 and senior PC for IJCAI 2023 and ECAI 2023.

  • 12/2022, I am hornored to receive the Australasian Artificial Intelligence Emerging Research Contribution Award.

  • 10/2022, congrats to Haopeng and Maggie for their papers accepted to WACV 2023.

  • 09/2022, congrats to Aoqi and Erdun for their papers accepted to NeurIPS 2022. Our collaborative work with the PGM group at University of Adelaide on efficient differentiable DAG learning also got accepted.

  • 08/2022, I was promoted to Senior Lecturer (grateful to my students and collaborators).

  • 08/2022, I will serve as an Area Chair for ICLR 2023.

  • 08/2022, I was selected to join the editorial board of Machine Learning Journal.

  • 07/2022, I was awarded the CCF-Tencent Rhino-Bird Young Faculty Open Research Fund. Thank you Tencent and CCF.

  • 07/2022, congrats to Dongting for his first paper accepted to ECCV 2022. Our collaborative work with Alibaba on Adaptive Sparse Radiance Grid also got accepted.

  • 07/2022, Prof Nengkun Yu gave us a wonderful talk on quantum computing and learning.

  • 06/2022, congrats to Haopeng for his paper accepted to IEEE T-PAMI.

  • 04/2022, I was selected as one of Global Top Young Chinese Scholars in AI by Baidu Scholar 2022.

  • 03/2022, I will serve as an Area Chair for NeurIPS 2022.

  • 03/2022, our collaborative work with Ebay on recommender systems was accepted to SIGIR 2022.

  • 03/2022, five papers (2 on image-to-image translation, 2 on self-supervised learning, and 1 collaborative work with Baidu on few-shot font style transfer) were accepted to CVPR 2022.

  • 01/2022, our paper on statistical/causal fair learning under label noise were accepted to CLeaR 2022.

  • 01/2022, four papers (1 on causal robustness, 1 on causal RL, 2 on weakly-supervised learning) were accepted to ICLR 2022.

  • 12/2021, I will serve as an Area Chair for ICML 2022.

  • 11/2021, Our Python package for causal discovery causal-learn was released.

  • 11/2021, I will serve as an Area Chair for UAI 2022.

  • 10/2021, our papers on causal treatment of domain adaptation and label noise learning were accepted to NeurIPS 2021.

  • 07/2021, I will be the Area Chair and Publicity Chair at the 1st conference on Causal Learning and Reasoning (CLeaR).

See more in News.