Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for James Cheng

James Cheng

Improving Graph Representation Learning by Contrastive Regularization


Jan 27, 2021
Kaili Ma, Haochen Yang, Han Yang, Tatiana Jin, Pengfei Chen, Yongqiang Chen, Barakeel Fanseu Kamhoua, James Cheng

Figure 1 for Improving Graph Representation Learning by Contrastive Regularization
Figure 2 for Improving Graph Representation Learning by Contrastive Regularization
Figure 3 for Improving Graph Representation Learning by Contrastive Regularization
Figure 4 for Improving Graph Representation Learning by Contrastive Regularization

  Access Paper or Ask Questions

The item selection problem for user cold-start recommendation


Oct 27, 2020
Yitong Meng, Jie Liu, Xiao Yan, James Cheng

Figure 1 for The item selection problem for user cold-start recommendation
Figure 2 for The item selection problem for user cold-start recommendation
Figure 3 for The item selection problem for user cold-start recommendation
Figure 4 for The item selection problem for user cold-start recommendation

  Access Paper or Ask Questions

Rethinking Graph Regularization For Graph Neural Networks


Sep 04, 2020
Han Yang, Kaili Ma, James Cheng

Figure 1 for Rethinking Graph Regularization For Graph Neural Networks
Figure 2 for Rethinking Graph Regularization For Graph Neural Networks
Figure 3 for Rethinking Graph Regularization For Graph Neural Networks
Figure 4 for Rethinking Graph Regularization For Graph Neural Networks

  Access Paper or Ask Questions

Understanding Graph Neural Networks from Graph Signal Denoising Perspectives


Jun 08, 2020
Guoji Fu, Yifan Hou, Jian Zhang, Kaili Ma, Barakeel Fanseu Kamhoua, James Cheng

Figure 1 for Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
Figure 2 for Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
Figure 3 for Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
Figure 4 for Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
* 19 pages, 8 figures 
  Access Paper or Ask Questions

Boosting First-order Methods by Shifting Objective: New Schemes with Faster Worst Case Rates


May 25, 2020
Kaiwen Zhou, Anthony Man-Cho So, James Cheng

Figure 1 for Boosting First-order Methods by Shifting Objective: New Schemes with Faster Worst Case Rates
Figure 2 for Boosting First-order Methods by Shifting Objective: New Schemes with Faster Worst Case Rates
Figure 3 for Boosting First-order Methods by Shifting Objective: New Schemes with Faster Worst Case Rates
* 27 pages, 7 figures 
  Access Paper or Ask Questions

TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism


Apr 16, 2020
Zhenkun Cai, Kaihao Ma, Xiao Yan, Yidi Wu, Yuzhen Huang, James Cheng, Teng Su, Fan Yu

Figure 1 for TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism
Figure 2 for TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism
Figure 3 for TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism
Figure 4 for TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism

  Access Paper or Ask Questions

Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs


Mar 16, 2020
Han Yang, Xiao Yan, Xinyan Dai, James Cheng

Figure 1 for Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
Figure 2 for Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
Figure 3 for Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
Figure 4 for Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs

  Access Paper or Ask Questions

Edit Distance Embedding using Convolutional Neural Networks


Jan 31, 2020
Xinyan Dai, Xiao Yan, Kaiwen Zhou, Yuxuan Wang, Han Yang, James Cheng

Figure 1 for Edit Distance Embedding using Convolutional Neural Networks
Figure 2 for Edit Distance Embedding using Convolutional Neural Networks
Figure 3 for Edit Distance Embedding using Convolutional Neural Networks
Figure 4 for Edit Distance Embedding using Convolutional Neural Networks

  Access Paper or Ask Questions

Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning


Nov 25, 2019
Xinyan Dai, Xiao Yan, Kaiwen Zhou, Han Yang, Kelvin K. W. Ng, James Cheng, Yu Fan

Figure 1 for Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning
Figure 2 for Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning
Figure 3 for Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning
Figure 4 for Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning

  Access Paper or Ask Questions

Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search


Nov 20, 2019
Xinyan Dai, Xiao Yan, Kelvin K. W. Ng, Jie Liu, James Cheng

Figure 1 for Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search
Figure 2 for Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search
Figure 3 for Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search
Figure 4 for Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search

  Access Paper or Ask Questions

Understanding and Improving Proximity Graph based Maximum Inner Product Search


Sep 30, 2019
Jie Liu, Xiao Yan, Xinyan Dai, Zhirong Li, James Cheng, Ming-Chang Yang

Figure 1 for Understanding and Improving Proximity Graph based Maximum Inner Product Search
Figure 2 for Understanding and Improving Proximity Graph based Maximum Inner Product Search
Figure 3 for Understanding and Improving Proximity Graph based Maximum Inner Product Search
Figure 4 for Understanding and Improving Proximity Graph based Maximum Inner Product Search
* 8 pages, 8 figures 
  Access Paper or Ask Questions

Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)


Nov 05, 2018
Xiao Yan, Xinyan Dai, Jie Liu, Kaiwen Zhou, James Cheng

Figure 1 for Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)
Figure 2 for Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)
Figure 3 for Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)
Figure 4 for Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)

  Access Paper or Ask Questions

VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning


Oct 28, 2018
Fanhua Shang, Kaiwen Zhou, Hongying Liu, James Cheng, Ivor W. Tsang, Lijun Zhang, Dacheng Tao, Licheng Jiao

Figure 1 for VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
Figure 2 for VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
Figure 3 for VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
Figure 4 for VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
* 46 pages, 25 figures. IEEE Transactions on Knowledge and Data Engineering, accepted in October, 2018. arXiv admin note: substantial text overlap with arXiv:1704.04966 
  Access Paper or Ask Questions

Norm-Ranging LSH for Maximum Inner Product Search


Oct 22, 2018
Xiao Yan, Jinfeng Li, Xinyan Dai, Hongzhi Chen, James Cheng

Figure 1 for Norm-Ranging LSH for Maximum Inner Product Search
Figure 2 for Norm-Ranging LSH for Maximum Inner Product Search
Figure 3 for Norm-Ranging LSH for Maximum Inner Product Search
* NIPS2018 
  Access Paper or Ask Questions

Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications


Oct 11, 2018
Fanhua Shang, James Cheng, Yuanyuan Liu, Zhi-Quan Luo, Zhouchen Lin

Figure 1 for Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications
Figure 2 for Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications
Figure 3 for Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications
Figure 4 for Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications
* IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(9): 2066-2080, 2018 
 * 29 pages, 19 figures 
  Access Paper or Ask Questions

ASVRG: Accelerated Proximal SVRG


Oct 07, 2018
Fanhua Shang, Licheng Jiao, Kaiwen Zhou, James Cheng, Yan Ren, Yufei Jin

Figure 1 for ASVRG: Accelerated Proximal SVRG
Figure 2 for ASVRG: Accelerated Proximal SVRG
Figure 3 for ASVRG: Accelerated Proximal SVRG
Figure 4 for ASVRG: Accelerated Proximal SVRG
* 32 pages, 3 figures 
  Access Paper or Ask Questions

A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates


Jun 28, 2018
Kaiwen Zhou, Fanhua Shang, James Cheng

Figure 1 for A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
Figure 2 for A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
Figure 3 for A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
Figure 4 for A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
* ICML2018 
  Access Paper or Ask Questions

Tractable and Scalable Schatten Quasi-Norm Approximations for Rank Minimization


Feb 28, 2018
Fanhua Shang, Yuanyuan Liu, James Cheng

Figure 1 for Tractable and Scalable Schatten Quasi-Norm Approximations for Rank Minimization
Figure 2 for Tractable and Scalable Schatten Quasi-Norm Approximations for Rank Minimization
Figure 3 for Tractable and Scalable Schatten Quasi-Norm Approximations for Rank Minimization
Figure 4 for Tractable and Scalable Schatten Quasi-Norm Approximations for Rank Minimization
* 26 pages, 7 figures, AISTATS 2016. arXiv admin note: text overlap with arXiv:1606.01245 
  Access Paper or Ask Questions

Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization


Feb 26, 2018
Fanhua Shang, Yuanyuan Liu, Kaiwen Zhou, James Cheng, Kelvin K. W. Ng, Yuichi Yoshida

Figure 1 for Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization
Figure 2 for Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization
Figure 3 for Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization
Figure 4 for Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization
* 24 pages, 10 figures, AISTATS 2018. arXiv admin note: text overlap with arXiv:1703.06807 
  Access Paper or Ask Questions

Accelerated Variance Reduced Stochastic ADMM


Jul 11, 2017
Yuanyuan Liu, Fanhua Shang, James Cheng

Figure 1 for Accelerated Variance Reduced Stochastic ADMM
Figure 2 for Accelerated Variance Reduced Stochastic ADMM
Figure 3 for Accelerated Variance Reduced Stochastic ADMM
Figure 4 for Accelerated Variance Reduced Stochastic ADMM
* 16 pages, 5 figures, Appears in Proceedings of the 31th AAAI Conference on Artificial Intelligence (AAAI), San Francisco, California, USA, pp. 2287--2293, 2017 
  Access Paper or Ask Questions

Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent


Jun 04, 2017
Fanhua Shang, Yuanyuan Liu, James Cheng, Kelvin Kai Wing Ng, Yuichi Yoshida

Figure 1 for Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent
Figure 2 for Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent
Figure 3 for Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent
Figure 4 for Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent
* 25 pages, 8 figures 
  Access Paper or Ask Questions

Fast Stochastic Variance Reduced Gradient Method with Momentum Acceleration for Machine Learning


Apr 17, 2017
Fanhua Shang, Yuanyuan Liu, James Cheng, Jiacheng Zhuo

Figure 1 for Fast Stochastic Variance Reduced Gradient Method with Momentum Acceleration for Machine Learning
Figure 2 for Fast Stochastic Variance Reduced Gradient Method with Momentum Acceleration for Machine Learning
Figure 3 for Fast Stochastic Variance Reduced Gradient Method with Momentum Acceleration for Machine Learning
Figure 4 for Fast Stochastic Variance Reduced Gradient Method with Momentum Acceleration for Machine Learning
* Corrected a few typos in this version 
  Access Paper or Ask Questions

Unified Scalable Equivalent Formulations for Schatten Quasi-Norms


Nov 27, 2016
Fanhua Shang, Yuanyuan Liu, James Cheng

* 21 pages. CUHK Technical Report CSE-ShangLC20160307, March 7, 2016 
  Access Paper or Ask Questions

Scalable Algorithms for Tractable Schatten Quasi-Norm Minimization


Jun 04, 2016
Fanhua Shang, Yuanyuan Liu, James Cheng

Figure 1 for Scalable Algorithms for Tractable Schatten Quasi-Norm Minimization
Figure 2 for Scalable Algorithms for Tractable Schatten Quasi-Norm Minimization
Figure 3 for Scalable Algorithms for Tractable Schatten Quasi-Norm Minimization
Figure 4 for Scalable Algorithms for Tractable Schatten Quasi-Norm Minimization
* 16 pages, 5 figures, Appears in Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI), Phoenix, Arizona, USA, pp. 2016--2022, 2016 
  Access Paper or Ask Questions

Regularized Orthogonal Tensor Decompositions for Multi-Relational Learning


Jan 16, 2016
Fanhua Shang, James Cheng, Hong Cheng

Figure 1 for Regularized Orthogonal Tensor Decompositions for Multi-Relational Learning
Figure 2 for Regularized Orthogonal Tensor Decompositions for Multi-Relational Learning
Figure 3 for Regularized Orthogonal Tensor Decompositions for Multi-Relational Learning
Figure 4 for Regularized Orthogonal Tensor Decompositions for Multi-Relational Learning
* 18 pages, 10 figures 
  Access Paper or Ask Questions

Structured Low-Rank Matrix Factorization with Missing and Grossly Corrupted Observations


Sep 03, 2014
Fanhua Shang, Yuanyuan Liu, Hanghang Tong, James Cheng, Hong Cheng

Figure 1 for Structured Low-Rank Matrix Factorization with Missing and Grossly Corrupted Observations
Figure 2 for Structured Low-Rank Matrix Factorization with Missing and Grossly Corrupted Observations
Figure 3 for Structured Low-Rank Matrix Factorization with Missing and Grossly Corrupted Observations
Figure 4 for Structured Low-Rank Matrix Factorization with Missing and Grossly Corrupted Observations
* 28 pages, 9 figures 
  Access Paper or Ask Questions

Generalized Higher-Order Tensor Decomposition via Parallel ADMM


Jul 05, 2014
Fanhua Shang, Yuanyuan Liu, James Cheng

Figure 1 for Generalized Higher-Order Tensor Decomposition via Parallel ADMM
Figure 2 for Generalized Higher-Order Tensor Decomposition via Parallel ADMM
Figure 3 for Generalized Higher-Order Tensor Decomposition via Parallel ADMM
Figure 4 for Generalized Higher-Order Tensor Decomposition via Parallel ADMM
* 9 pages, 5 figures, AAAI 2014 
  Access Paper or Ask Questions