371 citations · 3.9k across the 110 of their papers we have counts for
15 papers · 1 filter
Adversarial Feature Augmentation and Normalization for Visual Recognition
Tianlong Chen, Yu Cheng, Zhe Gan +4
Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective…
Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective
Tianlong Chen, Yu Cheng, Zhe Gan +2
Training generative adversarial networks (GANs) with limited real image data generally results in deteriorated performance and collapsed models. To conquer this challenge, we are i…
Wasserstein Contrastive Representation Distillation
Liqun Chen, Dong Wang, Zhe Gan +3
The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compa…
Efficient Robust Training via Backward Smoothing
Jinghui Chen, Yu Cheng, Zhe Gan +2
Adversarial training is so far the most effective strategy in defending against adversarial examples. However, it suffers from high computational costs due to the iterative adversa…
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
Pengyu Cheng, Weituo Hao, Shuyang Dai +3
Mutual information (MI) minimization has gained considerable interests in various machine learning tasks. However, estimating and minimizing MI in high-dimensional spaces remains a…
MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients
Chen Zhu, Yu Cheng, Zhe Gan +3
Adaptive gradient methods such as RMSProp and Adam use exponential moving estimate of the squared gradient to compute adaptive step sizes, achieving better convergence than SGD in…
APo-VAE: Text Generation in Hyperbolic Space
Shuyang Dai, Zhe Gan, Yu Cheng +3
Natural language often exhibits inherent hierarchical structure ingrained with complex syntax and semantics. However, most state-of-the-art deep generative models learn embeddings…
Graph-Driven Generative Models for Heterogeneous Multi-Task Learning
Wenlin Wang, Hongteng Xu, Zhe Gan +6
We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework. The proposed model is based on the fact that heterogen…
Improving Textual Network Learning with Variational Homophilic Embeddings
Wenlin Wang, Chenyang Tao, Zhe Gan +7
The performance of many network learning applications crucially hinges on the success of network embedding algorithms, which aim to encode rich network information into low-dimensi…
Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation
Shuyang Dai, Yu Cheng, Yizhe Zhang +3
Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order…
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
Yunchen Pu, Shuyang Dai, Zhe Gan +5
A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed m…
Topic Compositional Neural Language Model
Wenlin Wang, Zhe Gan, Wenqi Wang +5
We propose a Topic Compositional Neural Language Model (TCNLM), a novel method designed to simultaneously capture both the global semantic meaning and the local word ordering struc…
Adversarial Symmetric Variational Autoencoder
Yunchen Pu, Weiyao Wang, Ricardo Henao +4
A new form of variational autoencoder (VAE) is developed, in which the joint distribution of data and codes is considered in two (symmetric) forms: () from observed data fed thr…
Triangle Generative Adversarial Networks
Zhe Gan, Liqun Chen, Weiyao Wang +5
A Triangle Generative Adversarial Network (-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each…
VAE Learning via Stein Variational Gradient Descent
Yunchen Pu, Zhe Gan, Ricardo Henao +3
A new method for learning variational autoencoders (VAEs) is developed, based on Stein variational gradient descent. A key advantage of this approach is that one need not make para…