Xuhui Fan

Lecturer, Office 320, 4 Research Park Drive, School of Computing, Macquarie University Email: XUHUI.FAN [AT@AT] MQ [DOT] EDU [DOT] AU Github, Google Scholar

About me

I am currently a Lecturer in the School of Computing at the Macquarie University. Before that, I worked as a lecturer in the School of Information and Physical Sciences at the University of Newcastle, as a postdoctoral fellow in the School of Mathematics and Statistics at the University of New South Wales, and at Data61, CSIRO.

My Ph.D degree is obtained at the University of Technology, Sydney on May, 2015. Prior to coming to Australia, I received my Bachelor degree in Mathematical Statistics from the University of Science and Technology of China in 2010.

Research themes

Uncertainties exploration is my research focus. It includes the following tasks:

Temporal Uncertainties (Stochastic Point Process methods)

• Xuhui Fan, Edwin V. Bonilla, Terence J. O'Kane, Scott A. Sisson.
  “Free-Form Variational Inference for Gaussian Process State-Space Models”.
  The 40th International Conference on Machine Learning (ICML-23) Code.

• Xuhui Fan, Yaqiong Li, Ling Chen, Bin Li, Scott A. Sisson.
  “Hawkes processes with stochastic exogenous effects for continuous-time interaction modelling”.
  IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI) Code.

• Xuhui Fan, Bin Li, Feng Zhou, Scott A. Sisson.
  “Continuous-Time Edge Modelling using Non-Parametric Point Processes”.
  The 35th Conference on Neural Information Processing Systems (NeurIPS-21) Code.

Spatial Uncertainties (Bayesian Nonparametric Space Partition methods)

• Xuhui Fan, Bin Li, Ling Luo, Scott A. Sisson.
  “Bayesian Nonparametric Space Partitions: A Survey”.
  The 30th International Joint Conference on Artificial Intelligence - Survey Track (IJCAI-21-Survey Track).

• Xuhui Fan, Bin Li, Scott A. Sisson.
  “Online Binary Space Partitioning Forests”.
  The 23rd International Conference on Artificial Intelligence and Statistics (AISTATS-20) Code.

• Xuhui Fan, Bin Li, Scott A. Sisson.
  “Binary Space Partitioning Forests”.
  The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS- 19) Code.

• Xuhui Fan, Bin Li, Scott A. Sisson.
  “Rectangular Bounding Process”.
  The 32nd Conference on Neural Information Processing Systems (NeurIPS-18) Code.

• Xuhui Fan, Bin Li, Scott A. Sisson.
  “The Binary Space Partitioning-Tree process”.
  The 21st International Conference on Artificial Intelligence and Statistics (AISTATS- 18) Code.

Deep Architectures’ Uncertainties (Dirichlet Belief Networks)

• Xuhui Fan, Bin Li, Yaqiong Li, Scott A. Sisson.
  “Poisson-Randomised DirBN: Large Mutation is Needed in Dirichlet Belief Networks”.
  The 38th International Conference on Machine Learning (ICML-21) Code.

• Xuhui Fan, Bin Li, Scott A. Sisson, Caoyuan Li, Ling Chen.
  “Scalable Deep Generative Relational Models with High-Order Node Dependence”.
  The 33rd Conference on Neural Information Processing Systems (NeurIPS-19) Code.

Research

The research methods involved in the above tasks include

• Gaussian Processes

• Bayesian Nonparametric Space Partitions

• Deep Generative Models

• Stochastic Point Processes

• Variational Inference methods

• Markov chain Monte Carlo methods

Full list of publications.