b'James T. Kwok'

research

∙ 02/17/2022

Revisiting Over-smoothing in BERT from the Perspective of Graph

Recently over-smoothing phenomenon of Transformer-based models is observ...

Han Shi, et al. ∙

research

∙ 09/17/2021

Dropout's Dream Land: Generalization from Learned Simulators to Reality

A World Model is a generative model used to simulate an environment. Wor...

Zac Wellmer, et al. ∙

research

∙ 06/13/2021

Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution

Recently, deep convolutional neural network methods have achieved an exc...

Huapeng Wu, et al. ∙

research

∙ 06/13/2021

Feedback Pyramid Attention Networks for Single Image Super-Resolution

Recently, convolutional neural network (CNN) based image super-resolutio...

Huapeng Wu, et al. ∙

research

∙ 06/11/2021

TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation

In few-shot domain adaptation (FDA), classifiers for the target domain a...

Haoang Chi, et al. ∙

research

∙ 02/25/2021

SparseBERT: Rethinking the Importance Analysis in Self-attention

Transformer-based models are popular for natural language processing (NL...

Han Shi, et al. ∙

research

∙ 11/09/2020

A Survey of Label-noise Representation Learning: Past, Present and Future

Classical machine learning implicitly assumes that labels of the trainin...

Bo Han, et al. ∙

research

∙ 08/14/2020

Efficient Low-Rank Matrix Learning by Factorizable Nonconvex Regularization

Matrix learning is at the core of many machine learning problems. To enc...

Yaqing Wang, et al. ∙

research

∙ 11/26/2019

Effective Decoding in Graph Auto-Encoder using Triadic Closure

The (variational) graph auto-encoder and its variants have been popularl...

Han Shi, et al. ∙

research

∙ 05/27/2019

Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback

Communication overhead is a major bottleneck hampering the scalability o...

Shuai Zheng, et al. ∙

research

∙ 05/23/2019

Blockwise Adaptivity: Faster Training and Better Generalization in Deep Learning

Stochastic methods with coordinate-wise adaptive stepsize (such as RMSpr...

Shuai Zheng, et al. ∙

research

∙ 03/08/2019

General Convolutional Sparse Coding with Unknown Noise

Convolutional sparse coding (CSC) can learn representative shift-invaria...

Yaqing Wang, et al. ∙

research

∙ 06/08/2018

Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data

Variance reduction has been commonly used in stochastic optimization. It...

Shuai Zheng, et al. ∙

research

∙ 05/04/2018

Power Law in Sparsified Deep Neural Networks

The power law has been observed in the degree distributions of many biol...

Lu Hou, et al. ∙

research

∙ 04/27/2018

Online Convolutional Sparse Coding with Sample-Dependent Dictionary

Convolutional sparse coding (CSC) has been popularly used for the learni...

Yaqing Wang, et al. ∙

research

∙ 02/23/2018

Loss-aware Weight Quantization of Deep Networks

The huge size of deep networks hinders their use in small computing devi...

Lu Hou, et al. ∙

research

∙ 10/19/2017

Scalable Robust Matrix Factorization with Nonconvex Loss

Robust matrix factorization (RMF), which uses the ℓ_1-loss, often outper...

Quanming Yao, et al. ∙

research

∙ 10/19/2017

Efficient Robust Matrix Factorization with Nonconvex Loss

Robust matrix factorization (RMF), which uses the ℓ_1-loss, often outper...

Quanming Yao, et al. ∙

research

∙ 08/01/2017

Large-Scale Low-Rank Matrix Learning with Nonconvex Regularizers

Low-rank modeling has many important applications in computer vision and...

Quanming Yao, et al. ∙

research

∙ 06/21/2017

Scalable Online Convolutional Sparse Coding

Convolutional sparse coding (CSC) improves sparse coding by learning a s...

Yaqing Wang, et al. ∙

research

∙ 04/04/2017

Multi-Label Learning with Global and Local Label Correlation

It is well-known that exploiting label correlations is important to mult...

Yue Zhu, et al. ∙

research

∙ 03/16/2017

Accelerated and Inexact Soft-Impute for Large-Scale Matrix and Tensor Completion

Matrix and tensor completion aim to recover a low-rank matrix / tensor f...

Quanming Yao, et al. ∙

research

∙ 11/05/2016

Loss-aware Binarization of Deep Networks

Deep neural network models, though very powerful and highly successful, ...

Lu Hou, et al. ∙

research

∙ 06/13/2016

Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity

The use of convex regularizers allows for easy optimization, though they...

Quanming Yao, et al. ∙

research

∙ 04/24/2016

Stochastic Variance-Reduced ADMM

The alternating direction method of multipliers (ADMM) is a powerful opt...

Shuai Zheng, et al. ∙

research

∙ 02/25/2016

Fast Nonsmooth Regularized Risk Minimization with Continuation

In regularized risk minimization, the associated optimization problem be...

Shuai Zheng, et al. ∙

research

∙ 12/03/2015

Fast Low-Rank Matrix Learning with Nonconvex Regularization

Low-rank modeling has a lot of important applications in machine learnin...

Quanming Yao, et al. ∙

James T. Kwok

Featured Co-authors

Masashi Sugiyama

Jun Zhang

Tie-Yan Liu

Xiaodan Liang

Tongliang Liu

Feng Liu

Bo Han

Gang Niu

Zhenguo Li

Zhi-Hua Zhou

Ivor W. Tsang

Revisiting Over-smoothing in BERT from the Perspective of Graph

Dropout's Dream Land: Generalization from Learned Simulators to Reality

Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution

Feedback Pyramid Attention Networks for Single Image Super-Resolution

TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation

SparseBERT: Rethinking the Importance Analysis in Self-attention

A Survey of Label-noise Representation Learning: Past, Present and Future

Efficient Low-Rank Matrix Learning by Factorizable Nonconvex Regularization

Effective Decoding in Graph Auto-Encoder using Triadic Closure

Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback

Blockwise Adaptivity: Faster Training and Better Generalization in Deep Learning

General Convolutional Sparse Coding with Unknown Noise

Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data

Power Law in Sparsified Deep Neural Networks

Online Convolutional Sparse Coding with Sample-Dependent Dictionary

Loss-aware Weight Quantization of Deep Networks

Scalable Robust Matrix Factorization with Nonconvex Loss

Efficient Robust Matrix Factorization with Nonconvex Loss

Large-Scale Low-Rank Matrix Learning with Nonconvex Regularizers

Scalable Online Convolutional Sparse Coding

Multi-Label Learning with Global and Local Label Correlation

Accelerated and Inexact Soft-Impute for Large-Scale Matrix and Tensor Completion

Loss-aware Binarization of Deep Networks

Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity

Stochastic Variance-Reduced ADMM

Fast Nonsmooth Regularized Risk Minimization with Continuation

Fast Low-Rank Matrix Learning with Nonconvex Regularization