Mingming Gong


Home


Mingming Gong

Mingming Gong

Lecturer (Assistant Professor) in Data Science
School of Mathematics and Statistics
The University of Melbourne

Office: 111 Old Geology Building South, Parkville, VIC, Australia
E-mail: mingming.gong[at]unimelb.edu.au
Phone: +61-3-834-49211
[Google Scholar] [School Homepage]

I am a lecturer in Data Science at the School of Mathematics and Statistics, University of Melbourne (UoM). I am part of 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 Prof Kun Zhang. 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 or excellent 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!

  • The university provides various scholarships for PhD students, more detailed information can be found in the scholarship page. The application dealine for international students is Sep 30 and for domestic students is Oct 31.

  • To UoM Master/undergraduate students. Please be advised that I usually take 2 Master students and 1 undergraduate student each year. Please contact me if you have good GPA (WAM>80) and some coding skills.


Research Interests

My research interests lie in machine learning, artifical intelligence, and data science, especially in causal reasoning, transfer learning, and deep learning. I develop computational methods for causal reasoning from observational data and exploit causal knowledge to build more intelligent machine learning algorithms.

  • Causal Inference

  • Causality for Machine Learning, e.g., Transfer Learning

  • Deep Generative Models

  • Applications in Computer Vision, Biomedical Informatics, Financial Data Analysis, etc.


News

  • 04/2020, we are organizing the 3D Artificial Intelligence Challenge at the upcoming International Joint Conference on Artificial Intelligence (IJCAI20). Welcome to join us!

  • 12/2019, we are organizing the Weakly-supervised and Unsupervised Learning Workshop at the upcoming SIAM International Conference on Data Mining (SDM20). Welcome to join us!

  • 12/2019, I gave a talk on deep generative models and transfer learning at Institute of Computing Technology, Chinese Academy of Science, Beijing, China.

  • 12/2019, I gave a talk on causal discovery and transfer learning at Beijing International Center for Mathematical Research, Peking University, Beijing, China.

  • 12/2019, I gave a tutorial on causal learning in AI2019 and AusDM2019 held in Adelaide, Australia.

  • 11/2019, I gave a talk on causal learning in the Causal Modeling and Machine Learning workshop held in Guangzhou, China.

  • 11/2019, three papers accepted to AAAI2020.

  • 10/2019, I accepted the invitation to serve as a Senior PC for IJCAI 2020.

  • 09/2019, three papers (two spotlights) accepted to NeurIPS19.

  • 06/2019, I accepted the invitation to serve as a Senior PC for AAAI 2020.

  • 04/2019, our paper on causal discovery and forecasting in nonstationary environments has been accepted to ICML19.

  • 03/2019, I will join School of Mathematics and Statistics, The University of Melbourne, as a lecturer (assistant professor) on July 1st.

  • 02/2019, two papers (1 best paper finalist) accepted to CVPR19. Congrats to Huan Fu and Shanshan Zhao.

  • 02/2019, two papers accepted to AISTATS19. Congrats to Petar Stojanov.

  • 09/2018, our paper on modeling dynamic missingness in recommender systems has been accepted to NeurIPS18. Congrats to Menghan Wang.

  • 07/2018, three papers (1 oral) accepted to ECCV18. Congrats to Ya Li, Baosheng Yu, and Xiyu Yu.

  • 06/2018, our team won the 1st prize in single image depth prediction competition in Robust Vision Challenge 2018. Congrats to Huan Fu.

  • 06/2018, our paper on disease severity prediction has been accepted to MICCAI18. Congrats to Sumedha Singla.

  • 06/2018, our paper on causal discovery under measurement noise has been accepted to UAI18 as plenary presentation.

  • 02/2018, two papers have been accepted to CVPR18. Congrats to Huan Fu and Xiyu Yu.

  • 11/2017, our paper on domain generalization has been accepted to AAAI18 as oral presentation. Congrats to Ya Li.

  • 10/2017, our paper on pose estimation has been accepted to ICCV17 as spotlight presentation.

  • 06/2017, our paper entitled Causal Discovery from Temporally Aggregated Time Series has been accepted to UAI17.

  • 04/2017, I start working at University of Pittsburgh and Carnegie Mellon University as a postdoctoral research fellow.

  • 04/2016, our paper entitled Domain Adaptation with Conditional Transferable Components has been accepted to ICML16.


Research Highlights (* Equal Contribution)

    tacgan
  • M. Gong*, Y. Xu*, C. Li, K. Zhang, and K. Batmanghelich. Twin Auxiliary Classifiers GAN. In Neural Information Processing Systems (NeurIPS 2019). [PDF][CODE]

  • subsample
  • M. Gong*, K. Zhang*, B. Schölkopf, D. Tao, and P. Geiger. Discovering Temporal Causal Relations from Subsampled Data. In International Conference on Machine Learning (ICML 2015). [PDF][CODE]

  • M. Gong, K. Zhang, B. Schölkopf, C. Glymour, and D. Tao. Causal Discovery from Temporally Aggregated Time Series. In Conference on Uncertainty in Artificial Intelligence (UAI 2017). [PDF]

  • ctc
  • M. Gong, K. Zhang, T. Liu, D. Tao, C. Glymour, B. Schölkopf. Domain Adaptation with Conditional Transferable Components. In International Conference on Machine Learning (ICML 2016). [PDF][CODE].

  • depth
  • H. Fu, M. Gong, C. Wang, K. Batmanghelich, and D. Tao. Deep Ordinal Regression Network for Monocular Depth Estimation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018). [PDF][CODE].

  • gcgan
  • H. Fu*, M. Gong*, C. Wang, K. Batmanghelich, K. Zhang and D. Tao. Geometry-Consistent Adversarial Networks for One-Sided Unsupervised Domain Mapping. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019). [PDF][CODE].