Hi, I am Yifei Wang (ηŽ‹δΈ€ι£ž). I am generally interested in developing theoretical understandings and principled methods for machine learning. My works mainly lie in the areas of unsupervised learning (representation & generation), robust learning (adversarial & OOD robustness), and graph learning (GNN & Transformer).

I got my PhD (Applied Mathematics) in 2023 from Peking University (PKU), advised by Yisen Wang, Jiansheng Yang, and Zhouchen Lin. Prior to that, I received a BS in mathematics and a BA in philosophy from PKU. I am a recipient of Best ML Paper Award of ECML-PKDD 2021 and Silver Best Paper Award of ICML 2021 AdvML workshop.

Some links: Email / CV / Github / Twitter / Google Scholar

If you have questions regarding my work or have some interesting thoughts to discuss, just drop me an email.

News

Publications (* marks equal contribution)

  • Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective Yifei Wang*, Liangchen Li*, Jiansheng Yang, Zhouchen Lin, Yisen Wang NeurIPS 2023 2023 PDF
  • Adversarial Examples Are Not Real Features Ang Li*, Yifei Wang*, Yiwen Guo, Yisen Wang NeurIPS 2023 2023 PDF
  • Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding George Ma*, Yifei Wang*, Yisen Wang NeurIPS 2023 2023 PDF
  • Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning Xiaojun Guo*, Yifei Wang*, Zeming Wei, Yisen Wang NeurIPS 2023 2023 PDF
  • Tri-contrastive Learning: Identifiable Representation Learning with Automatic Discovery of Feature Importance Qi Zhang*, Yifei Wang*, Yisen Wang NeurIPS 2023 2023 PDF
  • On the Generalization of Multi-modal Contrastive Learning Qi Zhang*, Yifei Wang*, Yisen Wang ICML 2023 2023 PDF | Code
  • A Message Passing Perspective on Learning Dynamics of Contrastive Learning Yifei Wang*, Qi Zhang*, Tianqi Du, Jiansheng Yang, Zhouchen Lin, Yisen Wang ICLR 2023 2023 PDF | Code | Slides | Blog
  • Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism Zhijian Zhuo*, Yifei Wang*, Jinwen Ma, Yisen Wang ICLR 2023 2023 PDF | Code
  • Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning Rundong Luo*, Yifei Wang*, Yisen Wang ICLR 2023 2023 PDF | Code
  • ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond Xiaojun Guo*, Yifei Wang*, Tianqi Du*, Yisen Wang ICLR 2023 2023 PDF | Code
  • How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders Qi Zhang*, Yifei Wang*, Yisen Wang NeurIPS 2022 (Spotlight, Top 5%) 2022 PDF | Code | Slides
  • Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap Yifei Wang*, Qi Zhang*, Yisen Wang, Jiansheng Yang, Zhouchen Lin ICLR 2022 2022 PDF | Code | Slides
  • A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin ICLR 2022 (πŸ† Silver Best Paper Award @ ICML 2021 AdvML workshop) 2022 PDF | Slides | Award
  • Residual Relaxation for Multi-view Representation Learning Yifei Wang, Zhengyang Geng, Feng Jiang, Chuming Li, Yisen Wang, Jiansheng Yang, Zhouchen Lin NeurIPS 2021 2021 PDF | Slides | Blog
  • Dissecting the Diffusion Process in Linear Graph Convolutional Networks Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin NeurIPS 2021 2021 PDF | Code | Slides | Blog
  • Reparameterized Sampling for Generative Adversarial Networks Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin ECML-PKDD 2021 2021 (πŸ† Best ML Paper Award (1/685). Invited to Machine Learning Journal) PDF | Code | Slides | Media | Talk | Award
  • Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective Yifei Wang*, Liangchen Li*, Jiansheng Yang, Zhouchen Lin, Yisen Wang NeurIPS 2023 2023 PDF
  • Adversarial Examples Are Not Real Features Ang Li*, Yifei Wang*, Yiwen Guo, Yisen Wang NeurIPS 2023 2023 PDF
  • Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding George Ma*, Yifei Wang*, Yisen Wang NeurIPS 2023 2023 PDF
  • Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning Xiaojun Guo*, Yifei Wang*, Zeming Wei, Yisen Wang NeurIPS 2023 2023 PDF
  • Tri-contrastive Learning: Identifiable Representation Learning with Automatic Discovery of Feature Importance Qi Zhang*, Yifei Wang*, Yisen Wang NeurIPS 2023 2023 PDF
  • On the Generalization of Multi-modal Contrastive Learning Qi Zhang*, Yifei Wang*, Yisen Wang ICML 2023 2023 PDF | Code
  • Rethinking Weak Supervision in Helping Contrastive Representation Learning Jingyi Cui*, Weiran Huang*, Yifei Wang*, Yisen Wang ICML 2023 2023 PDF
  • CFA: Class-wise Calibrated Fair Adversarial Training Zeming Wei, Yifei Wang, Yiwen Guo, Yisen Wang CVPR 2023 2023 PDF
  • Equilibrium Image Denoising with Implicit Differentiation Qi Chen, Yifei Wang, Zhengyang Geng, Yisen Wang, Jiansheng Yang, and Zhouchen Lin IEEE Transactions on Image Processing (TIP) 2023 PDF
  • A Message Passing Perspective on Learning Dynamics of Contrastive Learning Yifei Wang*, Qi Zhang*, Tianqi Du, Jiansheng Yang, Zhouchen Lin, Yisen Wang ICLR 2023 2023 PDF | Code | Slides | Blog
  • Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism Zhijian Zhuo*, Yifei Wang*, Jinwen Ma, Yisen Wang ICLR 2023 2023 PDF | Code
  • Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning Rundong Luo*, Yifei Wang*, Yisen Wang ICLR 2023 2023 PDF | Code
  • ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond Xiaojun Guo*, Yifei Wang*, Tianqi Du*, Yisen Wang ICLR 2023 2023 PDF | Code
  • Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States Mingjie Li, Yifei Wang, Yisen Wang, Zhouchen Lin ICLR 2023 2023 PDF
  • What Contrastive Learning Learns Beyond Class-wise Features? Xingyuming Liu, Yifei Wang, Yisen Wang ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models (ME-FoMo) 2023 PDF
  • Rethinking the Necessity of Labels in Backdoor Defense Zidi Xiong, Dongxian Wu, Yifei Wang, Yisen Wang ICLR 2023 Workshop on Backdoor Attacks and Defenses in Machine Learning (BANDS) 2023 PDF
  • On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization Shiji Xin, Yifei Wang, Jingtong Su, Yisen Wang AAAI 2023 (Oral) 2023 PDF
  • How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders Qi Zhang*, Yifei Wang*, Yisen Wang NeurIPS 2022 (Spotlight, Top 5%) 2022 PDF | Code | Slides
  • Improving Out-of-distribution Robustness by Adversarial Training with Structured Priors Qixun Wang*, Yifei Wang*, Hong Zhu, Yisen Wang NeurIPS 2022 (Spotlight, Top 5%) 2022 PDF | Code | Slides
  • When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture Yichuan Mo, Dongxian Wu, Yifei Wang, Yiwen Guo, Yisen Wang NeurIPS 2022 (Spotlight, Top 5%) 2022 PDF | Code
  • Variational Energy-Based Models: A Probabilistic Framework for Contrastive Self-Supervised Learning Tianqi Du*, Yifei Wang*, Weiran Huang, Yisen Wang NeurIPS 2022 SSL Workshop 2022 PDF
  • AggNCE: Asymptotically Identifiable Contrastive Learning Jingyi Cui*, Weiran Huang*, Yifei Wang, Yisen Wang NeurIPS 2022 SSL Workshop (Oral) 2022 PDF
  • Efficient and Scalable Implicit Graph Neural Networks with Virtual Equilibrium Qi Chen, Yifei Wang, Yisen Wang, Jianlong Chang, Qi Tian, Jiansheng Yang, Zhouchen Lin IEEE BigData 2022 (Long Talk) 2022 PDF
  • Optimization-Induced Graph Implicit Nonlinear Diffusion Qi Chen, Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin ICML 2022 2022 PDF | Code
  • G2CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters Mingjie Li, Xiaojun Guo, Yifei Wang, Yisen Wang, Zhouchen Lin ICML 2022 2022 PDF
  • Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap Yifei Wang*, Qi Zhang*, Yisen Wang, Jiansheng Yang, Zhouchen Lin ICLR 2022 2022 PDF | Code | Slides
  • A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin ICLR 2022 (πŸ† Silver Best Paper Award @ ICML 2021 AdvML workshop) 2022 PDF | Slides | Award
  • Residual Relaxation for Multi-view Representation Learning Yifei Wang, Zhengyang Geng, Feng Jiang, Chuming Li, Yisen Wang, Jiansheng Yang, Zhouchen Lin NeurIPS 2021 2021 PDF | Slides | Blog
  • Dissecting the Diffusion Process in Linear Graph Convolutional Networks Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin NeurIPS 2021 2021 PDF | Code | Slides | Blog
  • Reparameterized Sampling for Generative Adversarial Networks Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin ECML-PKDD 2021 2021 (πŸ† Best ML Paper Award (1/685) & Invited to Machine Learning Journal) PDF | Code | Slides | Media | Talk | Award
  • Train Once, and Decode as You Like Chao Tian, Yifei Wang, Hao Cheng, Yijiang Lian, Zhihua Zhang COLING 2020 2020 PDF
  • Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning Xiaojun Guo*, Yifei Wang*, Zeming Wei, Yisen Wang NeurIPS 2023 2023 PDF
  • Tri-contrastive Learning: Identifiable Representation Learning with Automatic Discovery of Feature Importance Qi Zhang*, Yifei Wang*, Yisen Wang NeurIPS 2023 2023 PDF
  • On the Generalization of Multi-modal Contrastive Learning Qi Zhang*, Yifei Wang*, Yisen Wang ICML 2023 2023 PDF | Code
  • Rethinking Weak Supervision in Helping Contrastive Representation Learning Jingyi Cui*, Weiran Huang*, Yifei Wang*, Yisen Wang ICML 2023 2023 PDF
  • A Message Passing Perspective on Learning Dynamics of Contrastive Learning Yifei Wang*, Qi Zhang*, Tianqi Du, Jiansheng Yang, Zhouchen Lin, Yisen Wang ICLR 2023 2023 PDF | Code | Slides | Blog
  • Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism Zhijian Zhuo*, Yifei Wang*, Jinwen Ma, Yisen Wang ICLR 2023 2023 PDF | Code
  • Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning Rundong Luo*, Yifei Wang*, Yisen Wang ICLR 2023 2023 PDF | Code
  • ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond Xiaojun Guo*, Yifei Wang*, Tianqi Du*, Yisen Wang ICLR 2023 2023 PDF | Code
  • What Contrastive Learning Learns Beyond Class-wise Features? Xingyuming Liu, Yifei Wang, Yisen Wang ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models (ME-FoMo) 2023 PDF
  • Rethinking the Necessity of Labels in Backdoor Defense Zidi Xiong, Dongxian Wu, Yifei Wang, Yisen Wang ICLR 2023 Workshop on Backdoor Attacks and Defenses in Machine Learning (BANDS) 2023 PDF
  • How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders Qi Zhang*, Yifei Wang*, Yisen Wang NeurIPS 2022 (Spotlight, Top 5%) 2022 PDF | Code | Slides
  • Variational Energy-Based Models: A Probabilistic Framework for Contrastive Self-Supervised Learning Tianqi Du*, Yifei Wang*, Weiran Huang, Yisen Wang NeurIPS 2022 SSL Workshop 2022 PDF
  • AggNCE: Asymptotically Identifiable Contrastive Learning Jingyi Cui*, Weiran Huang*, Yifei Wang, Yisen Wang NeurIPS 2022 SSL Workshop (Oral) 2022 PDF
  • Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap Yifei Wang*, Qi Zhang*, Yisen Wang, Jiansheng Yang, Zhouchen Lin ICLR 2022 2022 PDF | Code | Slides
  • A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin ICLR 2022 (πŸ† Silver Best Paper Award @ ICML 2021 AdvML workshop) 2022 PDF | Slides | Award
  • Residual Relaxation for Multi-view Representation Learning Yifei Wang, Zhengyang Geng, Feng Jiang, Chuming Li, Yisen Wang, Jiansheng Yang, Zhouchen Lin NeurIPS 2021 2021 PDF | Slides | Blog
  • Reparameterized Sampling for Generative Adversarial Networks Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin ECML-PKDD 2021 2021 (πŸ† Best ML Paper Award (1/685). Invited to Machine Learning Journal) PDF | Code | Slides | Media | Talk | Award
  • Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective Yifei Wang*, Liangchen Li*, Jiansheng Yang, Zhouchen Lin, Yisen Wang NeurIPS 2023 2023 PDF
  • Adversarial Examples Are Not Real Features Ang Li*, Yifei Wang*, Yiwen Guo, Yisen Wang NeurIPS 2023 2023 PDF
  • CFA: Class-wise Calibrated Fair Adversarial Training Zeming Wei, Yifei Wang, Yiwen Guo, Yisen Wang CVPR 2023 2023 PDF
  • Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning Rundong Luo*, Yifei Wang*, Yisen Wang ICLR 2023 2023 PDF
  • Rethinking the Necessity of Labels in Backdoor Defense Zidi Xiong, Dongxian Wu, Yifei Wang, Yisen Wang ICLR 2023 Workshop on Backdoor Attacks and Defenses in Machine Learning (BANDS) 2023 PDF
  • On the Connection between Invariant Learning and Adversarial Training for Out-of-Distribution Generalization Shiji Xin, Yifei Wang, Jingtong Su, Yisen Wang AAAI 2023 (Oral) 2023 PDF
  • Improving Out-of-distribution Robustness by Adversarial Training with Structured Priors Qixun Wang*, Yifei Wang*, Hong Zhu, Yisen Wang NeurIPS 2022 (Spotlight, Top 5%) 2022 PDF | Code | Slides
  • When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture Yichuan Mo, Dongxian Wu, Yifei Wang, Yiwen Guo, Yisen Wang NeurIPS 2022 (Spotlight, Top 5%) 2022 PDF | Code
  • A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin ICLR 2022 (πŸ† Silver Best Paper Award @ ICML 2021 AdvML workshop) 2022 PDF | Slides | Award
  • Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding George Ma*, Yifei Wang*, Yisen Wang NeurIPS 2023 2023 PDF
  • Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning Xiaojun Guo*, Yifei Wang*, Zeming Wei, Yisen Wang NeurIPS 2023 2023 PDF
  • ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond Xiaojun Guo*, Yifei Wang*, Tianqi Du*, Yisen Wang ICLR 2023 2023 PDF
  • Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States Mingjie Li, Yifei Wang, Yisen Wang, Zhouchen Lin ICLR 2023 2023 PDF
  • Efficient and Scalable Implicit Graph Neural Networks with Virtual Equilibrium Qi Chen, Yifei Wang, Yisen Wang, Jianlong Chang, Qi Tian, Jiansheng Yang, Zhouchen Lin IEEE BigData 2022 (Long Talk) 2022 PDF
  • Optimization-Induced Graph Implicit Nonlinear Diffusion Qi Chen, Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin ICML 2022 2022 PDF | Code
  • G2CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters Mingjie Li, Xiaojun Guo, Yifei Wang, Yisen Wang, Zhouchen Lin ICML 2022 2022 PDF
  • Dissecting the Diffusion Process in Linear Graph Convolutional Networks Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin NeurIPS 2021 2021 PDF | Code | Slides | Blog

Selected Awards

Beijing Excellent Graduate Award, 2023
Excellent Graduate Award, Peking University, 2023
National Scholarship, 2021, 2022
Principal Scholarship, Peking University, 2022
Best ML Paper Award (1/685), ECML-PKDD, 2021
Silver Best Paper Award, ICML AdvML workshop, 2021

Professional Services

I served as a reviewer for the following main conferences and journals in the field of machine learning:
  • Conference: NeurIPS (2022, 2023), ICLR (2024), ICML (2022), AISTATS (2024), LoG (2023), ECML-PKDD (2022)
  • Journal: IEEE TPAMI
I also occasionally review for top-tier conferences in computer vision and and natural language processing:
  • CVPR (2023), ICCV (2023), ACL (ARR 2022)