Haiyan JIANG (she/her) - Postdoc Research Associate @ NYUAD


Publications


Currently, my research focuses on developing attack and defense algorithms for deep neural networks (DNNs) in both supervised and self-supervised learning, as well as adversarial machine learning. From 2022 to 2024, I worked on supervised training algorithms for spiking neural networks (SNNs), with an emphasis on direct supervised training and ANN-to-SNN conversion (i.e., transfer learning), collaborating with professors at MBZUAI. From 2020 to 2022, I focused on developing statistical machine learning algorithms at Baidu Research (China). Prior to that (2013–2020), my research was centered on time series prediction using neural networks. In the following list, denotes equal contribution, and ✉ indicates the corresponding author.

[Selected Conference Papers, Selected Journal Articles]


Selected Conference Papers

  1. H. Jiang, G.D. Masi, H. Xiong and B. Gu
    NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks.
    In International Conference on Machine Learning (ICML 2024) ,Vienna, Austria.
    [pdf] [OpenReview] [Code]

  2. H. Jiang, V. Zoonekynd, G.D. Masi, B. Gu, and H. Xiong
    TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks.
    In International Conference on Learning Representations (ICLR 2024) ,Vienna, Austria.
    [pdf] [OpenReview] [Code]

  3. H. Jiang, S. Anumasa, G.D. Masi, H. Xiong, and B. Gu
    A unified optimization framework of ANN-SNN Conversion: towards optimal mapping from activation values to firing rates.
    In International Conference on Machine Learning (ICML 2023) , Hawaii, US.
    [pdf] [OpenReview] [Code]

  4. Y. Zhang, H. Jiang, H. Ren, C. Zou, and D. Dou.
    AutoMS: Automatic model selection for novelty detection with error rate control.
    In Advances in Neural Information Processing Systems (NeurIPS 2022).
    [pdf] [Code]


Selected Journal Articles

  1. H. Jiang, S. Qin, and O.H.M. Padilla.
    Feature Grouping and Sparse Principal Component Analysis with Truncated Regularization.
    Stat, 12(1), 2023, e538.
    [Link] [Code] [arxiv]

  2. X. Li, H. Xiong, X. Li, X. Zhang, J. Liu, H. Jiang, Z. Chen, and D. Dou
    G-LIME: Statistical learning for local interpretations of deep neural networks using global priors.
    Artificial Intelligence 314 (2023): 103823.
    [pdf]

  3. H. Jiang, H. Xiong, D. Wu, J. Liu, and D. Dou.
    AgFlow: fast model selection of penalized PCA via implicit regularization effects of gradient flow.
    Machine Learning 110(8), 2021, 2131-2150.
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021)
    [Link] [arxiv]

  4. J. Liu, T. Huang, H. Xiong, J. Huang, J. Zhou, H. Jiang, G. Yang, H. Wang, and D. Dou
    Analysis of collective response reveals that Covid-19-related activities start from the end of 2019 in mainland China.
    medRxiv, 2020-10.
    [Link]

  5. H. Jiang, J. Li, and Z. Li
    Determining the number of change-point via high-dimensional cross-validation.
    Stat, 9(1), 2020, e284.
    [Link]