activity
20202022
most citedLearning with Feature-Dependent Label Noise: A Progressive Approach

32 citations · 65 across the 8 of their papers we have counts for

collaborators

8 papers

cs.LG20221 cited

A Manifold View of Adversarial Risk

Wenjia Zhang, Yikai Zhang, Xiaoling Hu +3

The adversarial risk of a machine learning model has been widely studied. Most previous works assume that the data lies in the whole ambient space. We propose to take a new angle a…

cs.LG20212 cited

Topological Detection of Trojaned Neural Networks

Songzhu Zheng, Yikai Zhang, Hubert Wagner +2

Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through…

cs.LG202132 cited

Learning with Feature-Dependent Label Noise: A Progressive Approach

Yikai Zhang, Songzhu Zheng, Pengxiang Wu +2

Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing…

cs.LG20214 cited

Stability of SGD: Tightness Analysis and Improved Bounds

Yikai Zhang, Wenjia Zhang, Sammy Bald +3

Stochastic Gradient Descent (SGD) based methods have been widely used for training large-scale machine learning models that also generalize well in practice. Several explanations h…

cs.LG20217 cited

Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach

Yikai Zhang, Hui Qu, Qi Chang +3

Recently, Generative Adversarial Networks (GANs) have demonstrated their potential in federated learning, i.e., learning a centralized model from data privately hosted by multiple…

cs.LG20208 cited

Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information

Qi Chang, Zhennan Yan, Lohendran Baskaran +5

As deep learning technologies advance, increasingly more data is necessary to generate general and robust models for various tasks. In the medical domain, however, large-scale and…