activity
20182021
most citedAGAN: Towards Automated Design of Generative Adversarial Networks

39 citations · 97 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG20192 cited

SecureGBM: Secure Multi-Party Gradient Boosting

Zhi Fengy, Haoyi Xiong, Chuanyuan Song +7

Federated machine learning systems have been widely used to facilitate the joint data analytics across the distributed datasets owned by the different parties that do not trust eac…

cs.LG2019

Towards Making Deep Transfer Learning Never Hurt

Ruosi Wan, Haoyi Xiong, Xingjian Li +2

Transfer learning have been frequently used to improve deep neural network training through incorporating weights of pre-trained networks as the starting-point of optimization for…

cs.LG201937 cited

NormLime: A New Feature Importance Metric for Explaining Deep Neural Networks

Isaac Ahern, Adam Noack, Luis Guzman-Nateras +3

The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently. Many successful approaches forgo global approximations i…

cs.LG201939 cited

AGAN: Towards Automated Design of Generative Adversarial Networks

Hanchao Wang, Jun Huan

Recent progress in Generative Adversarial Networks (GANs) has shown promising signs of improving GAN training via architectural change. Despite some early success, at present the d…

cs.LG2019

On the Noisy Gradient Descent that Generalizes as SGD

Jingfeng Wu, Wenqing Hu, Haoyi Xiong +3

The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning. While past studies confirm that the magnitude and t…

cs.LG2019

FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary

Yingzhen Yang, Jiahui Yu, Nebojsa Jojic +2

We present a novel method of compression of deep Convolutional Neural Networks (CNNs) by weight sharing through a new representation of convolutional filters. The proposed method r…