About Me

Hi, I am Xiaoxiao Li. I am an Assistant Professor in the Electrical and Computer Engineering Department and an Associate Member in the Computer Science Department at the University of British Columbia (UBC), leading the Trusted and Efficient AI (TEA) Lab. I am also a core faculty member of Blockchain@UBC, a member of Biomedical Imaging and Artificial Intelligence, and a member of LEAP project.

Before joining UBC, I was a postdoc in the Department of Computer Science at Princeton, working with Prof. Kai Li and Prof. Olga Troyanskaya. I obtained my Ph.D. degree in Biomedical Engineering from Yale University, where I was fortunate to be advised by Prof. James Duncan. I received Yale Advanced Graduate Leadership Fellowship. I obtained my B.S. (honors degree) from Chu Kochen College, Zhejiang University, China, in June 2015.

My current research lies in machine learning and its application to healthcare and blockchain. Our research topics cover deep learning, computer vision, trustworthy AI, data economy, medical image analysis and so on. I aim to narrow the gap between AI research and its applications by developing the next-generation trustworthy AI systems. What is trustworthy AI? Please read this survey.

Open Positions

If you want to work with me, please email me (click here) including your CV, transcript, and one of your research papers if applicable. Due to the large amount of emails I receive, I may not be able to respond to each one individually. To help me notice you email, please put "[ILOLLEH]", written backwards, in your email subject. Please strictly follow the instruction :)

  • Graduate Students: Multiple positions for graduate students are available for the study of machine learning, computer vision, NLP, trustworthy AI, or AI for healthcare. We do not make decision before seeing your application in the application system. Please refer to the polices of being a graduate student in our group.
  • Intern Students and Visiting Students/Scholars: All formats of local and remote collaboration are welcomed. For the intern students at UBC, we need to work together through course registration or summer internship programs.
  • News

  • [07/2022] One paper is accepted by ECCV 2022.
  • [06/2022] Three papers are accepted by MICCAI 2022.
  • [05/2022] Our work on launching effcient AI training on blockchain is accepted by BTS 2022.
  • [05/2022] Our Paper 'FedNI', an FL strategy for populataional diease analysis on distributed graphs, is accepted by TMI.
  • [04/2022] We receive ROCHE's and CIFAR's support on healthcare data synthesis project.
  • [03/2022] We receive NVIDIA Academic Hardware Grant to continuously support our FL projects. Thank Nvidia for the generous sponsorship.
  • [02/2022] I am selected as a Google Cloud Research Innovator.
  • [01/2022] One paper is accepted by ICLR 2022.
  • Recent Publications

    For the complete list, please check my google scholar. Email me if you have any questions about my papers or code, or if you would like to collaborate with me.

  • Class Impression for Data-free Incremental Learning.
    Ayromlou, S., Abolmaesumi, P., Tsang, T., Li, X. MICCAI 2022
  • GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis.
    Peng, L., Wang, N., Xu, J., Zhu, X., & Li, X. TMI 2022
    [paper] [code] [project]
  • FedNI: Federated Graph Learning with Network Inpainting for Population Based Disease Prediction.
    Peng, L., Wang, N., Dvornek, N., Zhu, X., & Li, X. TMI 2022
  • Unsupervised Federated Learning is Possible: A Case of Class-Conditional-Sharing Clients.
    Lu, N., Wang, Z., Li, X., Niu, G., Dou, Q., & Sugiyama, M., ICLR 2022
  • Evaluating Explainable AI on a Multi-Modal Medical Imaging Task: Can Existing Algorithms Fulfill Clinical Requirements?
    Jin, W., Li, X., & Hamarneh G., AAAI 2022
  • Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data.
    Huang, Y., Li, X., Yang, L., Gu, L., Zhu, Y., Seo, H., Meng, Q., Harada, T. & Sato, Y., BMVC 2021.
  • Subgraph Federated Learning with Missing Neighbor Generation.
    Zhang, K., Yang, C., Li, X., Sun, L., & Yiu, SM. NeurIPS 2021 (Spotlight).
    [paper] [code]
  • EMA: Auditing Data Removal from Trained Models.
    Huang, Y., Li, X.*, & Li, K. MICCAI 2021.
    [paper] [code]
  • FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis.
    Huang, B., Li, X., Song, Z., & Yang, X. ICML 2021.
  • FedBN: Federated Learning on Non-IID Features via Local Batch Normalization.
    Li, X., Jiang, M., Zhang, X., Kamp, M., & Dou, Q. ICLR 2021.
    [paper] [code]
  • On InstaHide, Phase Retrieval, and Sparse Matrix Factorization.
    Chen, S., Li, X., Song, Z., & Zhuo, D. ICLR 2021.
  • Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results.
    Li, X., Gu, Y., Dvornek, N., Staib, L., Ventola, P., & Duncan, J. S. Medical Image Analysis.
    [paper] [arxiv] [code]
  • Efficient Shapley Explanation For Features Importance Estimation Under Uncertainty.
    Li, X., Zhou, Y., Dvornek, N., Gu, Y., Ventola, P., & Duncan, J. S. MICCAI 2020.
    [paper] [code]
  • Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis.
    Li, X., Zhou, Y., Dvornek, N., Zhang, M., Zhuang, J, Ventola, P., & Duncan, J. S. MICCAI 2020.
    [paper] [arxiv] [code]
  • Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE.
    Zhuang, J., Dvornek, N.C., Li, X., Tatikonda, S., Papademetris, S.,and Duncan, J.S. ICML 2020.
    [paper] [arxiv] [code]
  • Recent Projects

    Here are my recent exciting projects. For the full list of my projects, please refer to my publications.

    Federated Learning on Non-iid Features via Local Batch Normalization

    Most of the previous federated learning work has focused on a difference in the distribution of labels. Unlike those settings, we address an important problem of FL, e.g., different scanner/sensors in medical imaging, where local clients may store examples with different marginal or conditional feature distributions compared to other nodes, which we denote as feature shift non-iid. In this work, we propose an effective method that uses local batch normalization to alleviate the feature shift before averaging models.

    Privacy-preserving Multi-site Medical Images Analysis

    We present a privacy-preserving federated learning framework for multi-site fMRI analysis. To overcome the domain shift issue, we have proposed two strategies: MoE and adversarial domain alignment to boost federated learning model performance. We have shown federated learning performance can potentially be boosted by adding domain adaptation and discussed the condition of benefits. Our approach brings new hope for accelerating deep learning applications in the field of medical imaging, where data isolation and the emphasis on data privacy have become challenges.

    BrainGNN: Explainable Graph Neural Network for Neuroimaging Analysis

    BrainGNN takes graphs built from neuroimages as inputs, and then outputs prediction results together with interpretation results.With the built-in interpretability, BrainGNN not only performs better on prediction than alternative methods, but also detects salient brain regions associated with predictions and discovers brain community patterns.

    DistDeepSHAP: Efficient Shapley Explanation for Feature Importance Estimation Under Uncertainty

    We propose DistDeepSHAP, a post-hoc feature importance estimation method under uncertainty evaluation for deep learning models.First, it can obtain uncertainty estimates for the provided feature importance scores. Second, it can better utilize the empirical distribution and has the potential for better feature importance scores estimation from the generated percentile saliency maps. Last but not least, it can compare with arbitrary subgroup references and interpret subgroup salient features, which is crucial for medical image study.


  • [06/2022] Keynote about Advancing AI in Healthcare with More and Diverse Data via Federated Learning at CVF/CVPR Medical Computer Vision Workshop and CWIT 2022. [Video]
  • [10/2021] Invited talk about "Trusted AI for Healthcare: from Theory to Practice" at Chinese University of Hong Kong, the University of Edinburgh, and MICS [Video(in Chineses)].
  • [02/2021] Invited talk about Trustworthy AI for Healthcare at Emory University.
  • [01/2021] Invited talk about Trustworthy AI for Healthcare at Istanbul Technical University.
  • [11/2020] Invited talk about BrainGNN at Tulane University and Lehigh University.
  • [09/2020] Invited talk about Multi-site Federated Learning for NeuroImaging Analysis at Chinese Academy of Sciences.
  • Teaching

  • [2017, 2018] ENAS 194: Ordinary and Partial Differential Equation (Yale University)
  • [2017, 2019] BENG 352: Biosignal Processing (Yale University)
  • [2021] COS 598D: Systems and Machine Learning (Princeton University) [Course website]
  • [2022] ELEC 400M: Machine Learning Fundamentals for Engineers (UBC) [Syllabus]
  • Students

  • Chun-Yin Huang (PhD student, 2021-, from CMU)
  • Wenlong Deng (PhD student, 2022-, from EPFL, co-supervised with Prof. Christos Thrampoulidis)
  • Minghui Chen (PhD student, 2022-, from SUSTC, co-supervised with Prof. Zehua Wang)
  • Sana Ayromlou (MSc student, 2021-, from Sharif University, co-supervised with Prof. Purang Abolmaesumi )
  • Beidi Zhao (MSc student, 2022-, from UESTC)
  • Ailar Mahdizadeh (MSc student, 2022-, from University of Tehran)
  • Justin Yang (MSc student, 2022-, from UBC, co-supervised with Prof. Mi Jung Park)
  • Nan Wang (Visting PhD student, from East China Normal University)
  • Fatemeh Taheri Dezaki (Postdoc, 2021, from UBC, now at Amazon, co-supervised with Prof. Purang Abolmaesumi)
  • Service

  • Associate Editor of Frontiers in NeuroImaging and Guest Editor of Algorithms
  • Organizer of NeurIPS 2021-2022 workshop on Medical Imaging Meets NeurIPS.
  • Organizer of ICML 2021-2022 workshop on Interpretable ML in Healthcare.
  • Organizer of MICCAI 2021/2022 workshop on Distributed, Collaborative, and Federated Learning
  • President of Women in MICCAI (2021-2023)
  • Reviewer of ICML, ICLR, NeurIPS, ICCV, AAAI, MICCAI, IPMI, TPAMI, Nature Machine Intelligence, MedIA, TMI, Neural Networks, etc.
  • Misc

    The books I am reading or have recently read:
  • Being Mortal: Medicine and What Matters in the End. ''We have been mistaken about what the mission of medical practitioners really is. We think our job is to ensure health and survival, but it should be more ambitious - our job is to help people be happy.''
  • The Shape of a Life.
  • Genghis Khan (Makers of History Series).
  • The Great Game .
  • The Three-Body Problem.
  • What It Takes: Lessons in the Pursuit of Excellence
  • The videos I want to share:
  • TED talk on Inside the mind of a master procrastinator.
  • Documentary: The Social Dilemma.
  • Documentary: Forging the Future.
  • Also, here are some blogs that may be benifitial for your career:
  • What a $500,000 grant proposal looks like