Alert button
Picture for Zhe Gan

Zhe Gan

Alert button

Efficient Robust Training via Backward Smoothing

Oct 03, 2020
Jinghui Chen, Yu Cheng, Zhe Gan, Quanquan Gu, Jingjing Liu

Figure 1 for Efficient Robust Training via Backward Smoothing
Figure 2 for Efficient Robust Training via Backward Smoothing
Figure 3 for Efficient Robust Training via Backward Smoothing
Figure 4 for Efficient Robust Training via Backward Smoothing
Viaarxiv icon

Contrastive Distillation on Intermediate Representations for Language Model Compression

Sep 29, 2020
Siqi Sun, Zhe Gan, Yu Cheng, Yuwei Fang, Shuohang Wang, Jingjing Liu

Figure 1 for Contrastive Distillation on Intermediate Representations for Language Model Compression
Figure 2 for Contrastive Distillation on Intermediate Representations for Language Model Compression
Figure 3 for Contrastive Distillation on Intermediate Representations for Language Model Compression
Figure 4 for Contrastive Distillation on Intermediate Representations for Language Model Compression
Viaarxiv icon

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

Sep 17, 2020
Yuwei Fang, Shuohang Wang, Zhe Gan, Siqi Sun, Jingjing Liu

Figure 1 for FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding
Figure 2 for FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding
Figure 3 for FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding
Figure 4 for FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding
Viaarxiv icon

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

Sep 13, 2020
Shuohang Wang, Luowei Zhou, Zhe Gan, Yen-Chun Chen, Yuwei Fang, Siqi Sun, Yu Cheng, Jingjing Liu

Figure 1 for Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding
Figure 2 for Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding
Figure 3 for Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding
Figure 4 for Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding
Viaarxiv icon

Accelerating Real-Time Question Answering via Question Generation

Sep 10, 2020
Yuwei Fang, Shuohang Wang, Zhe Gan, Siqi Sun, Jingjing Liu

Figure 1 for Accelerating Real-Time Question Answering via Question Generation
Figure 2 for Accelerating Real-Time Question Answering via Question Generation
Figure 3 for Accelerating Real-Time Question Answering via Question Generation
Figure 4 for Accelerating Real-Time Question Answering via Question Generation
Viaarxiv icon

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

Jul 14, 2020
Pengyu Cheng, Weituo Hao, Shuyang Dai, Jiachang Liu, Zhe Gan, Lawrence Carin

Figure 1 for CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
Figure 2 for CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
Figure 3 for CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
Figure 4 for CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
Viaarxiv icon

Graph Optimal Transport for Cross-Domain Alignment

Jun 29, 2020
Liqun Chen, Zhe Gan, Yu Cheng, Linjie Li, Lawrence Carin, Jingjing Liu

Figure 1 for Graph Optimal Transport for Cross-Domain Alignment
Figure 2 for Graph Optimal Transport for Cross-Domain Alignment
Figure 3 for Graph Optimal Transport for Cross-Domain Alignment
Figure 4 for Graph Optimal Transport for Cross-Domain Alignment
Viaarxiv icon