Yisen Wang's Homepage @Peking University

Yisen Wang 王奕森
Assistant Professor, Ph.D. Advisor
School of EECS, Peking University

Room 2201, Science Building #2
Peking University, No.5 Yiheyuan Road
Haidian District, Beijing 100871, China

Email: yisen.wang AT pku DOT edu.cn
Homepage (Overseas): https://sites.google.com/site/csyisenwang/
Homepage (Wall-inside): https://yisenwang.github.io/
Official Website: http://www.cis.pku.edu.cn/info/1084/1637.htm

[Google Scholar] [Github]

Biography

I am now a Tenure-track Assistant Professor (Ph.D. Advisor) in Department of Machine Intelligence, School of Electronics Engineering and Computer Science (EECS), Peking University. I am also a faculty member of ZERO Lab at Peking University led by Prof. Zhouchen Lin.

I got my PhD degree from Department of Computer Science and Technology, Tsinghua University in 2018. I have visited Georgia Tech, USA, hosted by Prof. Le Song and Prof. Hongyuan Zha, and The University of Melbourne, Australia, hosted by Prof. James Bailey.

My research interest broadly includes the theory and applications of machine learning and deep learning, such as adversarial learning, graph learning, and weakly/self-supervised learning.

Openings

We are recruiting highly motivated post-docs via Peking University Boya Postdoctoral Fellowship (Salary 350K+)

We are always actively recruiting Ph.D. students and interns! Welcome to contact me with your detailed CV!

News

3/2021, I will serve as Area Chair of NeurIPS 2021.

1/2021, Three papers were accepted to ICLR 2021 (Two are Spotlight, Top 4% = 114/2997)

10/2020, Our team (Dongxian Wu, Yisen Wang (advisor), Yanjie Li, Bin Chen) won the first prize in the 2020 GeekPwn CAAD AI MASK competitions.

10/2020, I will serve as Senior PC for IJCAI 2021.

9/2020, One paper was accepted to NeurIPS 2020.

Publications

( * Equal Contribution; # Corresponding Author)

Unlearnable Examples: Making Personal Data Unexploitable [PDF] [Code]
Hanxun Huang, Xingjun Ma#, Sarah Monazam Erfani, James Bailey, Yisen Wang#
International Conference on Learning Representations (ICLR 2021), 2021 (Spotlight, Top 4%)

Improving Adversarial Robustness via Channel-wise Activation Suppressing [PDF] [Code]
Yang Bai*, Yuyuan Zeng*, Yong Jiang, Shu-Tao Xia#, Xingjun Ma, Yisen Wang#
International Conference on Learning Representations (ICLR 2021), 2021 (Spotlight, Top 4%)

Towards A Unified Understanding and Improving of Adversarial Transferability [PDF] [Code]
Xin Wang*, Jie Ren*, Shuyun Lin, Xiangming Zhu, Yisen Wang, Quanshi Zhang
International Conference on Learning Representations (ICLR 2021), 2021

Adversarial Weight Perturbation Helps Robust Generalization [PDF] [Code] [NeurIPS MeetUp Video]
Dongxian Wu, Shu-Tao Xia, Yisen Wang#
Neural Information Processing Systems (NeurIPS 2020), 2020

Normalized Loss Functions for Deep Learning with Noisy Labels [PDF] [Code]
Xingjun Ma*, Hanxun Huang*, Yisen Wang#, Simone Romano, Sarah Erfani and James Bailey
International Conference on Machine Learning (ICML 2020), 2020

Improving Adversarial Robustness Requires Revisiting Misclassified Examples [PDF] [Code]
Yisen Wang*, Difan Zou*, Jinfeng Yi, James Bailey, Xingjun Ma, Quanquan Gu
International Conference on Learning Representations (ICLR 2020), Addis Ababa, Ethiopia, 2020

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets [PDF] [Code]
Dongxian Wu, Yisen Wang#, Shu-Tao Xia, James Bailey, Xingjun Ma
International Conference on Learning Representations (ICLR 2020), Addis Ababa, Ethiopia, 2020 (Spotlight)

Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles [PDF] [Code]
Ranjie Duan, Xingjun Ma, Yisen Wang, James Bailey, Kai Qin, Yun Yang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, USA, 2020

Improving Query Efficiency of Black-box Adversarial Attack [PDF] [Code]
Yang Bai*, Yuyuan Zeng*, Yong Jiang#, Yisen Wang#, Shu-Tao Xia, Weiwei Guo
European Conference on Computer Vision (ECCV 2020), 2020

Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems [PDF]
Xingjun Ma, Yuhao Niu, Lin Gu, Yisen Wang, Yitian Zhao, James Bailey, Feng Lu
Pattern Recognition (PR), 2020

On the Convergence and Robustness of Adversarial Training [PDF] [Code]
Yisen Wang*, Xingjun Ma*, James Bailey, Jinfeng Yi, Bowen Zhou, Quanquan Gu
International Conference on Machine Learning (ICML 2019), Long Beach, USA, 2019 (Long Talk)

Symmetric Cross Entropy for Robust Learning with Noisy Labels [PDF] [Code]
Yisen Wang*, Xingjun Ma*, Zaiyi Chen, Yuan Luo, Jinfeng Yi, James Bailey
International Conference on Computer Vision (ICCV 2019), Seoul, Korea, 2019

Hilbert-Based Generative Defense for Adversarial Examples [PDF]
Yang Bai*, Yan Feng*, Yisen Wang#, Shu-Tao Xia, Yong Jiang#
International Conference on Computer Vision (ICCV 2019), Seoul, Korea, 2019

Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in Dialogue Generation [PDF] [Code]
Min Zeng, Yisen Wang#, Yuan Luo
Conference on Empirical Methods in Natural Language Processing (EMNLP 2019), Hong Kong, China, 2019

Learning Deep Hidden Nonlinear Dynamics from Aggregate Data [PDF][Appendix]
Yisen Wang, Bo Dai, Lingkai Kong, Sarah Monazam Erfani, James Bailey, Hongyuan Zha
Conference on Uncertainty in Artificial Intelligence (UAI 2018), California, USA, 2018

Dimensionality-Driven Learning with Noisy Labels [PDF] [Code]
Xingjun Ma*, Yisen Wang*, Michael E. Houle, Shuo Zhou, Sarah Monazam Erfani, Shu-Tao Xia, Sudanthi Wijewickrema, James Bailey
International Conference on Machine Learning (ICML 2018), Stockholm, Sweden, 2018 (Long Talk)

Iterative Learning with Open-set Noisy Labels [PDF] [Code]
Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, Shu-Tao Xia
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, USA, 2018 (Spotlight)

Decoupled Networks [PDF] [Code]
Weiyang Liu, Zhen Liu, Zhiding Yu, Bo Dai, Rongmei Lin, Yisen Wang, James Rehg, Le Song
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018), Salt Lake City, USA, 2018 (Spotlight)

Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality [PDF] [Code]
Xingjun Ma, Bo Li, Yisen Wang, Sarah M. Erfani, Sudanthi Wijewickrema, Michael E. Houle, Grant Schoenebeck, Dawn Song, James Bailey
International Conference on Learning Representations (ICLR 2018), Vancouver, BC, Canada, 2018 (Oral)

A Novel Consistent Random Forest Framework: Bernoulli Random Forests [PDF]
Yisen Wang, Shu-Tao Xia, Qingtao Tang, Jia Wu, Xingquan Zhu
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2017

Link Sign Prediction by Variational Bayesian Probabilistic Matrix Factorization with Student-t Prior [PDF]
Yisen Wang*, Fangbing Liu, Shu-Tao Xia, Jia Wu
Information Sciences (IS), 2017

Residual convolutional CTC networks for automatic speech recognition [PDF]
Yisen Wang*, Xuejiao Deng*, Songpai Pu, Zhiheng Huang
Arxiv Technical Report, 2017

Unbiased Multivariate Correlation Analysis [PDF] [Appendix]
Yisen Wang, Simone Romano, Nguyen Vinh, James Bailey, Xingjun Ma, Shu-Tao Xia
AAAI Conference on Artificial Intelligence (AAAI 2017), San Francisco, California, USA, 2017. (Oral)

Unifying Attribute Splitting Criteria of Decision Trees by Tsallis Entropy [PDF]
Yisen Wang, Shu-Tao Xia
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017), New Orleans, USA, 2017.

Student-t Process Regression with Student-t Likelihood [PDF]
Qingtao Tang, Li Niu, Yisen Wang, Tao Dai, Wangpeng An, Jianfei Cai, Shu-Tao Xia
International Joint Conference on Artificial Intelligence (IJCAI 2017), Melbourne, Australia, 2017. (Oral)

Robust Survey Aggregation with Student-t Distribution and Sparse Representation [PDF]
Qingtao Tang, Tao Dai, Li Niu, Yisen Wang, Shu-Tao Xia, Jianfei Cai
International Joint Conference on Artificial Intelligence (IJCAI 2017), Melbourne, Australia, 2017. (Oral)

Bernoulli Random Forests: Closing the Gap between Theoretical Consistency and Empirical Soundness [PDF]
Yisen Wang, Qingtao Tang, Shu-Tao Xia, Jia Wu, Xingquan Zhu
International Joint Conference on Artificial Intelligence (IJCAI 2016), New York, USA, 2016. (Oral)

Student-t Process Regression with Dependent Student-t Noise [PDF]
Qingtao Tang, Yisen Wang, Shu-Tao Xia
European Conference on Artificial Intelligence (ECAI 2016), Hague, Netherlands, 2016. (Oral)

Academic Service

Associate Editor: Neurocomputing

Journal Reviewer: TPAMI, TIT, TIFS, TNNLS, TKDD, etc.

Conference Area Chair / Senior Program Committee: NeurIPS 2021, IJCAI 2021, ACML 2021.

Conference Program Committee: NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, AAAI, IJCAI, etc.

Talks

Rethinking the Min-max Problem for Adversarial Robustness [Event] [Slides]
Guest Lecture for CS 498@UIUC, Mar 2021.

Adversarial Machine Learning on Robustness, Privacy, and Architecture [Event] [Media]
BAAI Seminar Adversarial Machine Learning Session, Keynote Talk & Organizer, Feb 2021.

Adversarial Machine Learning and Beyond [Video]
Key Laboratory of Machine Perception (MOE) Annual Meeting, Peking University, Invited Talk & Organizer, Jan 2021.

Towards Trustworthy Machine Learning [Event]
LAMDA Lab, Nanjing University, Invited Talk, Nov 2020.

The Design of Robust Loss Function for Learning with Noisy Label [Event]
China Conference on Data Mining (CCDM) Workshop, Invited Talk, Aug 2020.

Awards

Baidu Scholarship (only 10 world-wide per year)

ACM China Doctoral Dissertation Nomination Award (only 5 nation-wide per year)

Tsinghua University Outstanding Doctoral Dissertation Award

Microsoft Research Fellowship Nomination Award

Best Paper Award at 9th International Doctoral Forum (Hong Kong)

National Scholarship for PhD Student

Lixin Tang Scholarship of Tsinghua University

Top 10 Undergraduate Excellence Award (only 10 awardees university-wide per year (10/25,000)

Meritorious Winner (First Prize) of MCM: The Mathematical Contest in Modeling

National Scholarship for Undergraduate Student

Last update : 3/1/2021