My name is Jiazhi Li. Currently, I am a Ph.D. student at the Department of Electrical and Computer Engineering, and a Graduate Research Assistant at Information Sciences Institute, both being units of USC Viterbi School of Engineering, under the supervision of Prof. Wael AbdAlmageed. My research interests primarily focus on machine learning fairness, generative models, and debiased representation learning. Previously, I received my Bachelor’s degree in Electrical Engineering from Beijing Institution of Technology in Beijing, China in 2018 and my Master’s degree in Electrical Engineering from the University of Southern California, U.S. in 2020.

I am currently seeking an internship in Summer 2024.

Publications

• SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering
  [Code]
  Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu, Hanchen Xie, Mohamed E Hussein, Wael AbdAlmageed, submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023.

• A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment
  Hanchen Xie, Jiageng Zhu, Mahyar Khayatkhoei, Jiazhi Li, Mohamed E. Hussein, Wael Abd-Almageed, accepted by International Conference on Machine Learning (ICML), 2023.

• A Critical Review of Predominant Bias in Machine Intelligence
  Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu, Hanchen Xie, Mohamed E Hussein, Wael AbdAlmageed, planning to be submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023.

• Ethics and Fairness for Diabetes Artificial Intelligence
  Jiazhi Li, Wael Abd-Almageed, accepted as the book chapter in “Diabetes Digital Health, Telehealth, and Artificial Intelligence, Elsevier”, 2024.

• Information-Theoretic Bounds on The Removal of Attribute-Specific Bias from Neural Networks
  Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu, Hanchen Xie, Mohamed E Hussein, Wael AbdAlmageed, accepted by Conference on Neural Information Processing Systems (NeurIPS) Workshops on Algorithmic Fairness through the Lens of Time, 2023.

• CAT: Controllable Attribute Translation for Fair Attribute Classification
  Jiazhi Li, Wael Abd-Almageed, accepted by European Conference on Computer Vision (ECCV) Workshops on VISION WITH BIASED OR SCARCE DATA, 2022.

• Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition
  [code]
  Jiazhi Li, Wael Abd-Almageed, accepted by IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2021.

• Automatic Analysis of Lateral Cephalograms Based on Multiresolution Decision Tree Regression Voting
  Shumeng Wang, Huiqi Li, Jiazhi Li, Yanjun Zhang, Bingshuang Zou, ccepted by Journal of Healthcare Engineering, 2018.

• An Investigation on the Position Encoding in Vision-Based Dynamics Prediction
  Jiageng Zhu, Hanchen Xie, Jiazhi Li, Mahyar Khayatkhoei, Wael AbdAlmageed, In-Submission, 2023.

• Shadow Datasets, New challenging datasets for Causal Representation Learning
  [code]
  Jiageng Zhu, Hanchen Xie, Jianhua Wu, Jiazhi Li, Mahyar Khayatkhoei, Mohamed E Hussein, Wael AbdAlmageed, Pre-Print, 2023.