Ning Zhang

Ning Zhang

University of Oxford

About me

I am a DPhil in the statistics department at the University of Oxford (Computational Discovery CDT), and my supervisors are Prof. Mihai Cucuringu and Prof. Xiaowen Dong. Prior to that, I received my MASc in Electrical and Computer Engineering from the University of British Columbia, and BSc in Physics from Nankai University. [Curriculum Vitae]
Contact: ning.zhang[at]stats[dot]ox[dot]ac[dot]uk

Research

My research interest lies in the intersection of statistics and computation. Currently, I am focusing on better understanding computational tasks on graphs using tools such as probability theory, statistics, spectral methods, optimization, etc. My research involves proposing data-driven algorithms together with mathematical proofs, and at the same time, I seek to understand the nature of the problems and algorithms through the lens of those proofs. I am excited to see the transformation of ideas across different research fields.

Publications and preprints

  • On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective
    Ning Zhang, Henry Kenlay, Li Zhang, Mihai Cucuringu, and Xiaowen Dong.
    arXiv

  • Spectral Clustering for Directed Graphs via Likelihood Estimation on Stochastic Block Models
    Ning Zhang, Xiaowen Dong, and Mihai Cucuringu.
    arXiv Code

  • On the Feasible Region of Efficient Algorithms for Attributed Graph Alignment
    Ziao Wang, Ning Zhang, Weina Wang, and Lele Wang.
    IEEE Transactions on Information Theory, May 2024.
    arXiv Journal

  • Attributed Graph Alignment
    Ning Zhang, Ziao Wang, Weina Wang, and Lele Wang.
    IEEE Transactions on Information Theory, 2024.
    arXiv Journal

  • A spatially constrained deep convolutional neural network for nerve fiber segmentation in corneal confocal microscopic images using inaccurate annotations
    Ning Zhang, Susan Francis, Rayaz A. Malik and Xin Chen.
    IEEE International Symposium on Biomedical Imaging, 2020.
    arXiv ISBI Code

Talks

  • Nov. 2023: Maximum Likelihood Estimation on Stochastic Blockmodels for Directed Graph Clustering at the 12th International Conference on Complex Networks and their Applications
  • Aug. 2021: Poster presentation at North American School of Information Theory (best poster prize!);
  • Jun. 2021: Attributed graph alignment at IEEE International Symposium on Information Theory;
  • Apr. 2020: Spatially constrained DCNN for image segmentation at IEEE International Symposium on Biomedical Imaging;

Teaching

  • Michaelmas term 2023, Probability and Statistics for Network Analysis
  • Fall 2021 - Spring 2022, STAT321 Stochastic Signals and Systems
  • Spring 2020, ELEC291 Electrical Engineering Design Studio I