Zi-Hao Qiu @ LAMDA

Modified: 2014/08/25 22:19 by admin - Uncategorized
ImageChinese name
Zi-Hao Qiu (Z.-H. Qiu)

Ph.D. Student
LAMDA Group
Department of Computer Science
National Key Laboratory for Novel Software Technology
Nanjing University

Laboratory: 113, Building of Computer Science and Technology, Xianlin Campus of Nanjing University
email: qiuzh@lamda.nju.edu.cn
Image

Currently I am a first year Ph.D. student of Department of Computer Science and Technology in Nanjing University and a member of LAMDA Group(LAMDA Publications), led by professor Zhi-Hua Zhou.



Edit

Supervisor

Professor Lijun Zhang.

Edit

Biography

  • After that, I admitted to study for a M.Sc. degree in Nanjing University without entrance examination.
  • From september 2021, I started my Ph.D. degree under the supervision of Professor Lijun Zhang.

Edit

Research Interest

I am interested in machine learning, data mining, and optimization.

Edit

Publications

  • Zi-Hao Qiu*, Quanqi Hu*, Yongjian Zhong, Lijun Zhang, and Tianbao Yang. Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence. In Proceedings of the 39th International Conference on Machine Learning (ICML '22), to appear, 2022. [paper] [code]
  • Zhuoning Yuan, Yuexin Wu, Zi-Hao Qiu, Xianzhi Du, Lijun Zhang, Denny Zhou, Tianbao Yang. Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance. In Proceedings of the 39th International Conference on Machine Learning (ICML’22), to appear, 2022.
  • Zi-Hao Qiu, Ying-Chun Jian, Qing-Guo Chen, and Lijun Zhang. Learning to Augment Imbalanced Data for Re-ranking Models. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM '21), pages 1478-1487, 2021.

Edit

Awards & Honors

  • Excellent Graduate of Nanjing University. Nanjing, 2019

Edit

Projects

  • I am a contributor of LibAUC , which is an open-source deep learning library for optimizing a wide spectrum of measures/losses. They can be organized into four categories: areas under the curves (e.g., AUROC, AUPRC), ranking meansures (e.g., mAP, NDCG), performance at the top (e.g., top-K variants of mAP and NDCG), and contrastive objectives.

Edit

Teaching Assistant



Mail:
National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China
(In Chinese:) 南京市栖霞区仙林大道163号,软件新技术国家重点实验室,210023。

Last modified: 2022-06-24