Zhe Gan

is this you? claim profile

∙ 0 followers
Duke University ∙ Microsoft

Research Assistant at Duke University

Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly

Training generative adversarial networks (GANs) with limited data genera...
02/28/2021 ∙ by Tianlong Chen, et al. ∙ 0 ∙ share

read it
Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling

The canonical approach to video-and-language learning (e.g., video quest...
02/11/2021 ∙ by Jie Lei, et al. ∙ 2 ∙ share

read it
EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets

Deep, heavily overparameterized language models such as BERT, XLNet and ...
12/31/2020 ∙ by Xiaohan Chen, et al. ∙ 0 ∙ share

read it
Wasserstein Contrastive Representation Distillation

The primary goal of knowledge distillation (KD) is to encapsulate the in...
12/15/2020 ∙ by Liqun Chen, et al. ∙ 0 ∙ share

read it
A Closer Look at the Robustness of Vision-and-Language Pre-trained Models

Large-scale pre-trained multimodal transformers, such as ViLBERT and UNI...
12/15/2020 ∙ by Linjie Li, et al. ∙ 1 ∙ share

read it
Cross-Thought for Sentence Encoder Pre-training

In this paper, we propose Cross-Thought, a novel approach to pre-trainin...
10/07/2020 ∙ by Shuohang Wang, et al. ∙ 0 ∙ share

read it
Multi-Fact Correction in Abstractive Text Summarization

Pre-trained neural abstractive summarization systems have dominated extr...
10/06/2020 ∙ by Yue Dong, et al. ∙ 0 ∙ share

read it
InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective

Large-scale language models such as BERT have achieved state-of-the-art ...
10/05/2020 ∙ by Boxin Wang, et al. ∙ 0 ∙ share

read it
Efficient Robust Training via Backward Smoothing

Adversarial training is so far the most effective strategy in defending ...
10/03/2020 ∙ by Jinghui Chen, et al. ∙ 1 ∙ share

read it
Contrastive Distillation on Intermediate Representations for Language Model Compression

Existing language model compression methods mostly use a simple L2 loss ...
09/29/2020 ∙ by Siqi Sun, et al. ∙ 0 ∙ share

read it
Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding

Transformer has become ubiquitous in the deep learning field. One of the...
09/13/2020 ∙ by Shuohang Wang, et al. ∙ 0 ∙ share

read it
Accelerating Real-Time Question Answering via Question Generation

Existing approaches to real-time question answering (RTQA) rely on learn...
09/10/2020 ∙ by Yuwei Fang, et al. ∙ 0 ∙ share

read it
FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding

Large-scale cross-lingual language models (LM), such as mBERT, Unicoder ...
09/10/2020 ∙ by Yuwei Fang, et al. ∙ 0 ∙ share

read it
Graph Optimal Transport for Cross-Domain Alignment

Cross-domain alignment between two sets of entities (e.g., objects in an...
06/26/2020 ∙ by Liqun Chen, et al. ∙ 9 ∙ share

read it
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information

Mutual information (MI) minimization has gained considerable interests i...
06/22/2020 ∙ by Pengyu Cheng, et al. ∙ 38 ∙ share

read it
Adaptive Learning Rates with Maximum Variation Averaging

Adaptive gradient methods such as RMSProp and Adam use exponential movin...
06/21/2020 ∙ by Chen Zhu, et al. ∙ 19 ∙ share

read it
Large-Scale Adversarial Training for Vision-and-Language Representation Learning

We present VILLA, the first known effort on large-scale adversarial trai...
06/11/2020 ∙ by Zhe Gan, et al. ∙ 6 ∙ share

read it
Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models

Recent Transformer-based large-scale pre-trained models have revolutioni...
05/15/2020 ∙ by Jize Cao, et al. ∙ 0 ∙ share

read it
Improving Adversarial Text Generation by Modeling the Distant Future

Auto-regressive text generation models usually focus on local fluency, a...
05/04/2020 ∙ by Ruiyi Zhang, et al. ∙ 0 ∙ share

read it
POINTER: Constrained Text Generation via Insertion-based Generative Pre-training

Large-scale pre-trained language models, such as BERT and GPT-2, have ac...
05/01/2020 ∙ by Yizhe Zhang, et al. ∙ 5 ∙ share

read it
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training

We present HERO, a Hierarchical EncodeR for Omni-representation learning...
05/01/2020 ∙ by Linjie Li, et al. ∙ 3 ∙ share

read it
Contextual Text Style Transfer

We introduce a new task, Contextual Text Style Transfer - translating a ...
04/30/2020 ∙ by Yu Cheng, et al. ∙ 0 ∙ share

read it
APo-VAE: Text Generation in Hyperbolic Space

Natural language often exhibits inherent hierarchical structure ingraine...
04/30/2020 ∙ by Shuyang Dai, et al. ∙ 0 ∙ share

read it
BachGAN: High-Resolution Image Synthesis from Salient Object Layout

We propose a new task towards more practical application for image gener...
03/26/2020 ∙ by Yandong Li, et al. ∙ 7 ∙ share

read it
VIOLIN: A Large-Scale Dataset for Video-and-Language Inference

We introduce a new task, Video-and-Language Inference, for joint multimo...
03/25/2020 ∙ by Jingzhou Liu, et al. ∙ 17 ∙ share

read it
Nested-Wasserstein Self-Imitation Learning for Sequence Generation

Reinforcement learning (RL) has been widely studied for improving sequen...
01/20/2020 ∙ by Ruiyi Zhang, et al. ∙ 0 ∙ share

read it
Graph-Driven Generative Models for Heterogeneous Multi-Task Learning

We propose a novel graph-driven generative model, that unifies multiple ...
11/20/2019 ∙ by Wenlin Wang, et al. ∙ 0 ∙ share

read it
Distilling the Knowledge of BERT for Text Generation

Large-scale pre-trained language model, such as BERT, has recently achie...
11/10/2019 ∙ by Yen-Chun Chen, et al. ∙ 0 ∙ share

read it
Hierarchical Graph Network for Multi-hop Question Answering

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop...
11/09/2019 ∙ by Yuwei Fang, et al. ∙ 0 ∙ share

read it
Discourse-Aware Neural Extractive Model for Text Summarization

Recently BERT has been adopted in state-of-the-art text summarization mo...
10/30/2019 ∙ by Jiacheng Xu, et al. ∙ 0 ∙ share

read it
Meta Module Network for Compositional Visual Reasoning

There are two main lines of research on visual reasoning: neural module ...
10/08/2019 ∙ by Wenhu Chen, et al. ∙ 0 ∙ share

read it
Improving Textual Network Learning with Variational Homophilic Embeddings

The performance of many network learning applications crucially hinges o...
09/30/2019 ∙ by Wenlin Wang, et al. ∙ 0 ∙ share

read it
FreeLB: Enhanced Adversarial Training for Language Understanding

Adversarial training, which minimizes the maximal risk for label-preserv...
09/25/2019 ∙ by Chen Zhu, et al. ∙ 0 ∙ share

read it
UNITER: Learning UNiversal Image-TExt Representations

Joint image-text embedding is the bedrock for most Vision-and-Language (...
09/25/2019 ∙ by Yen-Chun Chen, et al. ∙ 0 ∙ share

read it
What Makes A Good Story? Designing Composite Rewards for Visual Storytelling

Previous storytelling approaches mostly focused on optimizing traditiona...
09/11/2019 ∙ by Junjie Hu, et al. ∙ 0 ∙ share

read it
Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation

Recent unsupervised approaches to domain adaptation primarily focus on m...
09/11/2019 ∙ by Shuyang Dai, et al. ∙ 0 ∙ share

read it
TIGEr: Text-to-Image Grounding for Image Caption Evaluation

This paper presents a new metric called TIGEr for the automatic evaluati...
09/04/2019 ∙ by Ming Jiang, et al. ∙ 0 ∙ share

read it
Domain Adaptive Text Style Transfer

Text style transfer without parallel data has achieved some practical su...
08/25/2019 ∙ by Dianqi Li, et al. ∙ 0 ∙ share

read it
Patient Knowledge Distillation for BERT Model Compression

Pre-trained language models such as BERT have proven to be highly effect...
08/25/2019 ∙ by Siqi Sun, et al. ∙ 0 ∙ share

read it
Adversarial Domain Adaptation for Machine Reading Comprehension

In this paper, we focus on unsupervised domain adaptation for Machine Re...
08/24/2019 ∙ by Huazheng Wang, et al. ∙ 0 ∙ share

read it
Relation-aware Graph Attention Network for Visual Question Answering

In order to answer semantically-complicated questions about an image, a ...
03/29/2019 ∙ by Linjie Li, et al. ∙ 0 ∙ share

read it
Topic-Guided Variational Autoencoders for Text Generation

We propose a topic-guided variational autoencoder (TGVAE) model for text...
03/17/2019 ∙ by Wenlin Wang, et al. ∙ 0 ∙ share

read it
Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation

We present FAST NAVIGATOR, a general framework for action decoding, whic...
03/06/2019 ∙ by Liyiming Ke, et al. ∙ 6 ∙ share

read it
Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog

This paper presents Recurrent Dual Attention Network (ReDAN) for visual ...
02/01/2019 ∙ by Zhe Gan, et al. ∙ 0 ∙ share

read it
Improving Sequence-to-Sequence Learning via Optimal Transport

Sequence-to-sequence models are commonly trained via maximum likelihood ...
01/18/2019 ∙ by Liqun Chen, et al. ∙ 0 ∙ share

read it
Sequential Attention GAN for Interactive Image Editing via Dialogue

In this paper, we introduce a new task - interactive image editing via c...
12/20/2018 ∙ by Yu Cheng, et al. ∙ 0 ∙ share

read it
StoryGAN: A Sequential Conditional GAN for Story Visualization

In this work we propose a new task called Story Visualization. Given a m...
12/06/2018 ∙ by Yitong Li, et al. ∙ 0 ∙ share

read it
Sequence Generation with Guider Network

Sequence generation with reinforcement learning (RL) has received signif...
11/02/2018 ∙ by Ruiyi Zhang, et al. ∙ 0 ∙ share

read it
Adversarial Text Generation via Feature-Mover's Distance

Generative adversarial networks (GANs) have achieved significant success...
09/17/2018 ∙ by Liqun Chen, et al. ∙ 0 ∙ share

read it
Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

Responses generated by neural conversational models tend to lack informa...
09/16/2018 ∙ by Yizhe Zhang, et al. ∙ 0 ∙ share

read it

Zhe Gan

Featured Co-authors