I am a third-year undergraduate at School of Mathematical Sciences, Peking University. Currently, I am a visiting student at UC Berkeley. I am interested in improving the trustworthiness of Machine Learning, specifically focusing on adversarial robustness and explainability.

🔥 News

  • 2023.09:  🔍 I was nominated to serve as a reviewer for ICLR 2024.
  • 2023.09:  🎉 1 Paper (as first author) accepted by Journal of Logical and Algebraic Methods in Programming.
  • 2023.08:  🏫 I started a visiting student program at UC Berkeley in Fall 2023.
  • 2023.07:  🏖 I attended ICML 2023 at Honolulu and illustrated our workshop poster.
  • 2023.07:  🔍 I reviewed 11 papers for NeurIPS 2023 (9 regular + 2 ethics).
  • 2023.06:  🎉 1 Paper (as first author & corresponding author) accepted by ICML 2023 AdvML-Frontiers Workshop.
  • 2023.06:  🍁 I attended CVPR 2023 at Vancouver and illustrated our poster.
  • 2023.05:  🥈 Won Second prize in Chinese Mathematics Competitions for College Students (National final).
  • 2023.05:  💡 Our patent An image classification method based on fair and robust neural networks has been published.
  • 2023.05:  🎙 I gave a talk on our CVPR paper in Safe & Responsible AI workshop (ICLR 2023 social event) at Tsinghua University.
  • 2023.02:  🎉 1 Paper (as first author) accepted by CVPR 2023.
  • 2022.12:  🥇 Won First prize in Chinese Mathematics Competitions for College Students (Beijing Division), and qualified for the finals.

📝 Publications

(*: Equal Contribution; ${}^\dagger$: Corresponding Author)

CFA: Class-wise Calibrated Fair Adversarial Training (CVPR 2023)

Zeming Wei, Yifei Wang, Yiwen Guo, Yisen Wang${}^\dagger$

  • Theoretically and empirically investigate the preference of different classes for adversarial configurations in Adversarial Training (AT)
  • Propose a CFA framework that customizes specific training configurations for each class automatically
  • CFA improves both overall robustness and fairness, and can be easily incorporated into other AT variants
  • [pdf] [arxiv] [code]

Sharpness-Aware Minimization Alone can Improve Adversarial Robustness (ICML 2023 Workshop)

Zeming Wei*${}^{\boldsymbol\dagger}$, Jingyu Zhu*, Yihao Zhang*

  • Theoretically show that using Sharpness-Aware Minimization (SAM) can improve adversarial robustness
  • Empirically illustrate that SAM can improve robustness with a friendly computational cost and no decrease in natural accuracy
  • Propose that SAM can be regarded as a lightweight substitute for AT under certain requirements
  • [pdf] [arxiv] [code]

Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languages (ICFEM 2022)

Zeming Wei, Xiyue Zhang, Meng Sun${}^\dagger$

  • Identify the transition sparsity and the context dependency problem in WFA extraction from RNNs in natural language tasks
  • Propose an extraction approach that complements the missing rules and enhances the context-aware ability
  • Our extraction framework is scalable to natural language tasks and of better extraction precision
  • [pdf] [arxiv] [code]

Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks (Journal of Logical and Algebraic Methods in Programming)

Zeming Wei, Xiyue Zhang, Yihao Zhang, Meng Sun${}^\dagger$

  • Extended version for ICFEM 2022 paper
  • Propose explaining Recurrent Neural Networks by the extracted automata with a transition-based word embedding
  • Further propose two applications (pertaining and adversarial attack) of the embedding
  • [pdf] [arxiv] [code]

💡 Patents

An image classification method based on fair and robust neural networks (patent pending)

Yisen Wang and Zeming Wei

🎖 Honors and Awards

  • Second prize, Chinese Mathematics Competitions for Undergraduates (National Final), 2023
  • First prize, Chinese Mathematics Competitions for Undergraduates (Beijing Division), 2022
  • Merit Student, Peking University, 2022
  • Huatai Science and Technology Scholarship, Peking University, 2022
  • Award for Contribution in Student Organizations, Peking University, 2021
  • Yang Fuqing & Wang Yangyuan Academician Scholarship, Peking University, 2021

📖 Educations

  • 2023.08 - 2023.12 (expected), Visiting Student, University of California Berkeley
  • 2021.06 - 2025.06 (expected), Undergraduate Student, School of Mathematical Sciences, Peking University
  • 2020.09 - 2021.06, Undergraduate Student, College of Engineering, Peking University
  • 2017.09 - 2020.06, Senior High School Student, Beijing No.4 High School

💼 Academic Service

  • Journal Reviewer: TMLR
  • Conference Reviewer: NeurIPS 2023, ICLR 2024
  • Workshop Reviewer: XAIA (@NeurIPS 2023)

🔗 Links

(Alphabetical Order)