699 citations · 3.7k across the 65 of their papers we have counts for
15 papers · 1 filter
A Generic Approach for Enhancing GANs by Regularized Latent Optimization
Yufan Zhou, Chunyuan Li, Changyou Chen +1
With the rapidly growing model complexity and data volume, training deep generative models (DGMs) for better performance has becoming an increasingly more important challenge. Prev…
Contrastive Attraction and Contrastive Repulsion for Representation Learning
Huangjie Zheng, Xu Chen, Jiangchao Yao +7
Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative sampl…
Partition-Guided GANs
Mohammadreza Armandpour, Ali Sadeghian, Chunyuan Li +1
Despite the success of Generative Adversarial Networks (GANs), their training suffers from several well-known problems, including mode collapse and difficulties learning a disconne…
Hierarchical Graph Capsule Network
Jinyu Yang, Peilin Zhao, Yu Rong +4
Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data. However, existing GNNs suffer from limited capability in c…
Implicit Deep Latent Variable Models for Text Generation
Le Fang, Chunyuan Li, Jianfeng Gao +2
Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth lat…
Twin Auxiliary Classifiers GAN
Mingming Gong, Yanwu Xu, Chunyuan Li +2
Conditional generative models enjoy remarkable progress over the past few years. One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly…
Towards Amortized Ranking-Critical Training for Collaborative Filtering
Sam Lobel, Chunyuan Li, Jianfeng Gao +1
Collaborative filtering is widely used in modern recommender systems. Recent research shows that variational autoencoders (VAEs) yield state-of-the-art performance by integrating f…
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
Hao Fu, Chunyuan Li, Xiaodong Liu +3
Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. The VAE objective consists of two terms, (i) rec…
Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning
Ruqi Zhang, Chunyuan Li, Jianyi Zhang +2
The posteriors over neural network weights are high dimensional and multimodal. Each mode typically characterizes a meaningfully different representation of the data. We develop Cy…
Adversarial Learning of a Sampler Based on an Unnormalized Distribution
Chunyuan Li, Ke Bai, Jianqiao Li +3
We investigate adversarial learning in the case when only an unnormalized form of the density can be accessed, rather than samples. With insights so garnered, adversarial learning…
Policy Optimization as Wasserstein Gradient Flows
Ruiyi Zhang, Changyou Chen, Chunyuan Li +1
Policy optimization is a core component of reinforcement learning (RL), and most existing RL methods directly optimize parameters of a policy based on maximizing the expected total…
Measuring the Intrinsic Dimension of Objective Landscapes
Chunyuan Li, Heerad Farkhoor, Rosanne Liu +1
Many recently trained neural networks employ large numbers of parameters to achieve good performance. One may intuitively use the number of parameters required as a rough gauge of…
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…