Alert button
Picture for Ji Liu

Ji Liu

Alert button

Central Server Free Federated Learning over Single-sided Trust Social Networks

Oct 11, 2019
Chaoyang He, Conghui Tan, Hanlin Tang, Shuang Qiu, Ji Liu

Figure 1 for Central Server Free Federated Learning over Single-sided Trust Social Networks
Figure 2 for Central Server Free Federated Learning over Single-sided Trust Social Networks
Figure 3 for Central Server Free Federated Learning over Single-sided Trust Social Networks
Figure 4 for Central Server Free Federated Learning over Single-sided Trust Social Networks
Viaarxiv icon

An Interactive Control Approach to 3D Shape Reconstruction

Oct 07, 2019
Bipul Islam, Ji Liu, Anthony Yezzi, Romeil Sandhu

Figure 1 for An Interactive Control Approach to 3D Shape Reconstruction
Figure 2 for An Interactive Control Approach to 3D Shape Reconstruction
Figure 3 for An Interactive Control Approach to 3D Shape Reconstruction
Figure 4 for An Interactive Control Approach to 3D Shape Reconstruction
Viaarxiv icon

Global Sparse Momentum SGD for Pruning Very Deep Neural Networks

Sep 27, 2019
Xiaohan Ding, Guiguang Ding, Xiangxin Zhou, Yuchen Guo, Ji Liu, Jungong Han

Figure 1 for Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
Figure 2 for Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
Figure 3 for Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
Figure 4 for Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
Viaarxiv icon

PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions

Sep 25, 2019
Shupeng Gui, Xiangliang Zhang, Pan Zhong, Shuang Qiu, Mingrui Wu, Jieping Ye, Zhengdao Wang, Ji Liu

Figure 1 for PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
Figure 2 for PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
Figure 3 for PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
Figure 4 for PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
Viaarxiv icon

$\texttt{DeepSqueeze}$: Decentralization Meets Error-Compensated Compression

Aug 03, 2019
Hanlin Tang, Xiangru Lian, Shuang Qiu, Lei Yuan, Ce Zhang, Tong Zhang, Ji Liu

Figure 1 for $\texttt{DeepSqueeze}$: Decentralization Meets Error-Compensated Compression
Viaarxiv icon

$\texttt{DeepSqueeze}$: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression

Jul 17, 2019
Hanlin Tang, Xiangru Lian, Shuang Qiu, Lei Yuan, Ce Zhang, Tong Zhang, Ji Liu

Figure 1 for $\texttt{DeepSqueeze}$: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Viaarxiv icon

Stochastic Convergence Results for Regularized Actor-Critic Methods

Jul 13, 2019
Wesley Suttle, Zhuoran Yang, Kaiqing Zhang, Ji Liu

Figure 1 for Stochastic Convergence Results for Regularized Actor-Critic Methods
Figure 2 for Stochastic Convergence Results for Regularized Actor-Critic Methods
Viaarxiv icon

A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning

Jul 06, 2019
Yixuan Lin, Kaiqing Zhang, Zhuoran Yang, Zhaoran Wang, Tamer Başar, Romeil Sandhu, Ji Liu

Viaarxiv icon

DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression

May 15, 2019
Hanlin Tang, Xiangru Lian, Tong Zhang, Ji Liu

Figure 1 for DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Figure 2 for DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Figure 3 for DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Figure 4 for DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Viaarxiv icon

Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend

Mar 28, 2019
Yawei Zhao, Chen Yu, Peilin Zhao, Ji Liu

Figure 1 for Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
Figure 2 for Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
Figure 3 for Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
Figure 4 for Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
Viaarxiv icon