Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Zhaowei Zhu

Demystifying How Self-Supervised Features Improve Training from Noisy Labels


Oct 18, 2021
Hao Cheng, Zhaowei Zhu, Xing Sun, Yang Liu


  Access Paper or Ask Questions

A Good Representation Detects Noisy Labels


Oct 12, 2021
Zhaowei Zhu, Zihao Dong, Hao Cheng, Yang Liu


  Access Paper or Ask Questions

The Rich Get Richer: Disparate Impact of Semi-Supervised Learning


Oct 12, 2021
Zhaowei Zhu, Tianyi Luo, Yang Liu


  Access Paper or Ask Questions

Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels


Feb 10, 2021
Zhaowei Zhu, Yiwen Song, Yang Liu


  Access Paper or Ask Questions

Identification of 27 abnormalities from multi-lead ECG signals: An ensembled Se-ResNet framework with Sign Loss function


Jan 12, 2021
Zhaowei Zhu, Xiang Lan, Tingting Zhao, Yangming Guo, Pipin Kojodjojo, Zhuoyang Xu, Zhuo Liu, Siqi Liu, Han Wang, Xingzhi Sun, Mengling Feng


  Access Paper or Ask Questions

A Second-Order Approach to Learning with Instance-Dependent Label Noise


Dec 22, 2020
Zhaowei Zhu, Tongliang Liu, Yang Liu

* Learning with label noise 

  Access Paper or Ask Questions

Federated Bandit: A Gossiping Approach


Oct 24, 2020
Zhaowei Zhu, Jingxuan Zhu, Ji Liu, Yang Liu

* 31 pages, 1 figure 

  Access Paper or Ask Questions

Learning with Instance-Dependent Label Noise: A Sample Sieve Approach


Oct 05, 2020
Hao Cheng, Zhaowei Zhu, Xingyu Li, Yifei Gong, Xing Sun, Yang Liu


  Access Paper or Ask Questions

Policy Learning Using Weak Supervision


Oct 05, 2020
Jingkang Wang, Hongyi Guo, Zhaowei Zhu, Yang Liu


  Access Paper or Ask Questions

Online optimal task offloading with one-bit feedback


Jul 02, 2018
Shangshu Zhao, Zhaowei Zhu, Fuqian Yang, Xiliang Luo

* We have submitted this paper to GlobalSIP 2018 on Jun. 29th 

  Access Paper or Ask Questions

Learn and Pick Right Nodes to Offload


Apr 24, 2018
Zhaowei Zhu, Ting Liu, Shengda Jin, Xiliang Luo

* 8 pages, 4 figures 

  Access Paper or Ask Questions