17 citations · 21 across the 5 of their papers we have counts for
6 papers
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training
Yifei Wang, Yisen Wang, Jiansheng Yang +1
Adversarial Training (AT) is known as an effective approach to enhance the robustness of deep neural networks. Recently researchers notice that robust models with AT have good gene…
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap
Yifei Wang, Qi Zhang, Yisen Wang +2
Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. I…
Residual Relaxation for Multi-view Representation Learning
Yifei Wang, Zhengyang Geng, Feng Jiang +4
Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation. In this paper, we no…
Reparameterized Sampling for Generative Adversarial Networks
Yifei Wang, Yisen Wang, Jiansheng Yang +1
Recently, sampling methods have been successfully applied to enhance the sample quality of Generative Adversarial Networks (GANs). However, in practice, they typically have poor sa…
Dissecting the Diffusion Process in Linear Graph Convolutional Networks
Yifei Wang, Yisen Wang, Jiansheng Yang +1
Graph Convolutional Networks (GCNs) have attracted more and more attentions in recent years. A typical GCN layer consists of a linear feature propagation step and a nonlinear trans…
Decoder-free Robustness Disentanglement without (Additional) Supervision
Yifei Wang, Dan Peng, Furui Liu +3
Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevi…