Wei Zhu

Wei Zhu

Applied Scientist at AWS

Wei Zhu’s Homepage, Amazon

Hi, I am Wei Zhu and am now an applied scientist at Amazon. I received my Ph. D. degree from the University or Rochester(UR) advised by Prof. Jiebo Luo and my M.S. and B.E. degree from Northwestern Polytechnical University, Xi’an China in 2018 and 2015 advised by Prof. Feiping Nie and Prof. Xuelong Li.

I am interested in prompt engineering, parameter efficient tuning, representation learning, fairness/debiasing/domain generalization, federated learning, graph neural network, few-shot learning and their applications in natural images, molecular graph, multivariate time series data, and medical images.

Email: zwvews@gmail.com

last update: Mar. 2023

Publications: Google Scholar

Parameter Efficient Tuning

  1. W. Zhu, R. Zhou, Y. Yao, C. Timothy, R. Jain, and J. Luo, “SegPrompt: Using Segmentation Map as a Better Prompt to Finetune Deep Models for Kidney Stone Classification”, MIDL, 2023.

Domain Generalization/Fairness/Debiasing

  1. W. Zhu, L. Lu, J. Xiao, M. Han, J. Luo, and A. P. Harrison, “Localized Adversarial Domain Generalization,” CVPR 2022. paper, code [domain generalization], [adversarial learning]
  2. W. Zhu, Z. Zheng, H. Liao, W. Li, and J. Luo, “Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization,” ICCV 2021. paper, code [debiasing/fairness], [mutual information estimation]

Federated Learning

  1. W. Zhu and J. Luo, “Federated Medical Image Analysis with Virtual Sample Synthesis,” MICCAI 2022 (early accept). paper, code [federated learning], [medical image analysis], [adversarial training]
  2. W. Zhu, Andrew White, and J. Luo, “Federated Learning of Molecular Properties in a Heterogeneous Setting,” Patterns 2022. paper, code [federated learning], [graph neural network]
  3. W. Zhu, D. Song, Y. Chen, W. Cheng, B. Zong, T. Mizoguchi, C. Lumezanu, H. Chen, and J. Luo, “Federated Anomaly Detection]{Deep Federated Anomaly Detection for Multivariate Time Series Data”, IEEE Big Data, 2022.

Few-Shot Learning

  1. W. Zhu, W. Li, H. Liao, and J. Luo, “Temperature Network for Few-shot Learning with Distribution-aware Large-margin Metric,” Pattern Recognition 2021. paper, code [few-shto leanring], [metric learning]
  2. W. Zhu, H. Liao, W. Li, W. Li, and J. Luo, “Alleviating the Incompatibility between Cross Entropy Loss and Episode Training for Few-shot Skin Disease Classification,” MICCAI 2020 (early accept). paper [few-shot learning], [contrastive learning], [metric learning]

Spectral-based Methods

  1. W. Zhu, F. Shi and J. Luo, “Modeling Heterogeneity in Feature Selection for MCI Classification”, ISBI 2020. paper [feature selection], [clustering]
  2. F. Nie, W. Zhu and X. Li, “Unsupervised Large Graph Embedding Based on Balanced and Hierarchical K-means,” TKDE 2020. paper [clustering], [metric learning]
  3. F. Nie, W. Zhu and X. Li, “Structured Graph Optimization for Unsupervised Feature Selection,” TKDE 2019. paper [feature selection]
  4. W. Zhu, F. Nie and X. Li, “Fast Spectral Clustering with Efficient Large Graph Embedding,” ICASSP 2017. paper [clustering], [metric learing]
  5. F. Nie, W. Zhu and X. Li, “Unsupervised Large Graph Embedding,” AAAI 2017. paper [metric learning]
  6. F. Nie, W. Zhu and X. Li, “Unsupervised Feature Selection with Structured Graph Optimization,” AAAI 2016, 1302-1308. paper [feature selection]

Others

  1. W. Zhu, W. Li, R. Dorsey, and J. Luo, “Unsupervised Anomaly Detection by Densely Contrastive Learning for Time Series Data”, Neural Network, 2023.
  2. A. Kolokythas, W. Zhu, and J. Luo, “Use of Artificial Intelligence in the Characterization of Oral Mucosal Lesions”, Journal of Oral and Maxillofacial Surgery, 2022.
  3. W. Zhu, Z. Zheng, H. Zheng, H. Lyu, and J. Luo, “Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis”, ICPR 2022 (early accept). paper [noisy labels]
  4. W. Li, W. Zhu, R. Dorsey, J. Luo, “Predicting Parkinson’s Disease with Multimodal Irregularly Collected Longitudinal Smartphone Data”, ICDM 2020. paper [multivarite time series]
  5. F. Nie, W. Zhu and X. Li, “Decision Tree SVM: An Extension of Linear SVM for Non-linear Classification,” Neurocomputing 2020. paper [SVM]

Educations

  • Ph.D. in Computer Science (Sep. 2018 - May. 2023)
    • Department of Computer Science, University of Rochester, Advisor: Prof. Jiebo Luo
      • Representation Learning, Federated Learning, and Domain Generalization/Debiasing
  • M.S. in Computer Science (Sep. 2015 - May. 2018)
    • School of Computer Science, Northwestern Polytechnical University, Xi’an
  • B.E. in Software Engineering (Sep. 2011 - Jul. 2015)
    • School of Software and Microelectronics, Northwestern Polytechnical University, Xi’an

Experiences

  • Applied Scientist @Amazon, CA (Apr. 2023 - present)
  • Summer intern @Amazon, CA: work with Dr. Haofu Liao (May. 2022 - Aug. 2022)
    • HOI detection
  • Summer intern @PAII, MD: work with Dr. Adam P. Harrison (May. 2021 - Aug. 2021)
    • Domain Generalization for Steatosis Diagnosis based on Ultrasound Images
  • Summer intern @NEC, NJ: work with Prof. Dongjin Song and Dr. Yuncong Chen (May. 2020 - Aug. 2020)
    • Federated Anomaly Detection
  • Summer intern @Siemens, NJ: work with Dr. Zhoubing Xu (May. 2019 - Aug. 2019)
    • Self-supervised learning with CT images
  • Summer intern @United-Imaging, Shanghai: work with Dr. Feng Shi (May. 2018 - Aug. 2018)
    • MCI Diagnosis

Professonal Activities

  • Reviewer for CVPR, AAAI, ECCV, ICPR, IEEE TNNLS, IEEE TII, IEEE TSP, IEEE/CAA JAS, IJIS, TMM, etc