陶略 Lue Tao Ph.D. Candidate, LAMDA Group School of Artificial Intelligence Nanjing University, Nanjing, China Supervisor: Professor Yuan Jiang and Professor Zhi-Hua Zhou Email: taol [at] lamda.nju.edu.cn

About Me

Currently I am a first year Ph.D. student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, led by Professor Zhi-Hua Zhou. I received my B.Sc. and M.Sc. degrees in computer science from Nanjing University of Aeronautics and Astronautics in 2019 and 2022, respectively, under the supervision of Professor Songcan Chen. In 2022, I was admitted to pursue Ph.D. degree in Nanjing University by passing the entrance examination.

Research Interests

My research interests include machine learning and data mining.

Publication

• Can Adversarial Training Be Manipulated By Non-Robust Features? [paper, code]
  Lue Tao, Lei Feng, Hongxin Wei, Jinfeng Yi, Sheng-Jun Huang, and Songcan Chen.
  In: Advances in Neural Information Processing Systems 35 (NeurIPS'22), in press, 2022.
  

• Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets. [paper]
  Hongxin Wei, Lue Tao, Renchunzi Xie, Lei Feng, and Bo An.
  In: Proceedings of the 39th International Conference on Machine Learning (ICML'22), pp. 23615-23630, 2022.
  

• With False Friends Like These, Who Can Notice Mistakes? [paper, code]
  Lue Tao, Lei Feng, Jinfeng Yi, and Songcan Chen.
  In: Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI'22), pp. 8458-8466, 2022.
  

• Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training. [paper, code]
  Lue Tao, Lei Feng, Jinfeng Yi, Sheng-Jun Huang, and Songcan Chen.
  In: Advances in Neural Information Processing Systems 34 (NeurIPS'21), pp. 16209-16225, 2021.
  

• Open-set Label Noise Can Improve Robustness Against Inherent Label Noise. [paper]
  Hongxin Wei, Lue Tao, Renchunzi Xie, and Bo An.
  In: Advances in Neural Information Processing Systems 34 (NeurIPS'21), pp. 7978-7992, 2021.
  

• Multiple-Instance Learning from Similar and Dissimilar Bags. [paper]
  Lei Feng, Senlin Shu, Yuzhou Cao, Lue Tao, Hongxin Wei, Tao Xiang, Bo An, and Gang Niu.
  In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'21), pp. 374-382, 2021.
  

• Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries. [paper]
  Kun-Peng Ning*, Lue Tao*, Songcan Chen, and Sheng-Jun Huang. (* indicates equal contribution)
  In: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI'21), pp. 9161-9169, 2021.
  

• Accelerated Stochastic Gradient-free and Projection-free Methods. [paper]
  Feihu Huang, Lue Tao, and Songcan Chen.
  In: Proceedings of the 37th International Conference on Machine Learning (ICML'20), pp. 4519-4530, 2020.
  

• Guided CNN for Generalized Zero-shot and Open-set Recognition Using Visual and Semantic Prototypes. [paper]
  Chuanxing Geng, Lue Tao, and Songcan Chen.
  In: Pattern Recognition, 102:107263, 2020.
  

Academic Service

• Reviewer for Conferences: ICML'21, NeurIPS'21, ILCR'22, IJCAI'22, ICML'22, NeurIPS'22, ICLR'23.
• Reviewer for Journals: TMLR.

Awards & Honors

• AAAI Student Scholarship, 2022

• National Scholarship for Undergraduates, 2018

• Grand Prize, 7th "China Software Cup" Software Design Competition for College Students, 2018 (rank: 1/4127)

Correspondence

Email: taol [at] lamda.nju.edu.cn
Office: Room 912, Computer Science Building, Xianlin Campus of Nanjing University
Address: National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China
(In Chinese: 南京市栖霞区仙林大道163号, 南京大学仙林校区603信箱, 软件新技术国家重点实验室, 210023)