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 Ming Yan

Ming Yan

Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs


Jul 26, 2021
Zhuoqing Song, Lei Shi, Shi Pu, Ming Yan

Figure 1 for Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs
Figure 2 for Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs

  Access Paper or Ask Questions

Elastic Graph Neural Networks


Jul 05, 2021
Xiaorui Liu, Wei Jin, Yao Ma, Yaxin Li, Hua Liu, Yiqi Wang, Ming Yan, Jiliang Tang

Figure 1 for Elastic Graph Neural Networks
Figure 2 for Elastic Graph Neural Networks
Figure 3 for Elastic Graph Neural Networks
Figure 4 for Elastic Graph Neural Networks
* ICML 2021 (International Conference on Machine Learning) 
  Access Paper or Ask Questions

Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks


Jun 14, 2021
Zhuoqing Song, Lei Shi, Shi Pu, Ming Yan

Figure 1 for Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks
Figure 2 for Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks
Figure 3 for Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks
* working paper 
  Access Paper or Ask Questions

E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning


Jun 04, 2021
Haiyang Xu, Ming Yan, Chenliang Li, Bin Bi, Songfang Huang, Wenming Xiao, Fei Huang

Figure 1 for E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Figure 2 for E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Figure 3 for E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Figure 4 for E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
* ACL2021 main conference 
  Access Paper or Ask Questions

StructuralLM: Structural Pre-training for Form Understanding


May 24, 2021
Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

Figure 1 for StructuralLM: Structural Pre-training for Form Understanding
Figure 2 for StructuralLM: Structural Pre-training for Form Understanding
Figure 3 for StructuralLM: Structural Pre-training for Form Understanding
Figure 4 for StructuralLM: Structural Pre-training for Form Understanding
* Accepted by ACL2021 main conference 
  Access Paper or Ask Questions

RCT: Resource Constrained Training for Edge AI


Mar 26, 2021
Tian Huang, Tao Luo, Ming Yan, Joey Tianyi Zhou, Rick Goh

Figure 1 for RCT: Resource Constrained Training for Edge AI
Figure 2 for RCT: Resource Constrained Training for Edge AI
Figure 3 for RCT: Resource Constrained Training for Edge AI
Figure 4 for RCT: Resource Constrained Training for Edge AI
* 14 pages 
  Access Paper or Ask Questions

SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels


Mar 14, 2021
Chenliang Li, Ming Yan, Haiyang Xu, Fuli Luo, Wei Wang, Bin Bi, Songfang Huang

Figure 1 for SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels
Figure 2 for SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels
Figure 3 for SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels
Figure 4 for SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels
* 10 pages, 4 figures 
  Access Paper or Ask Questions

CoRe: An Efficient Coarse-refined Training Framework for BERT


Nov 27, 2020
Cheng Yang, Shengnan Wang, Yuechuan Li, Chao Yang, Ming Yan, Jingqiao Zhang, Fangquan Lin

Figure 1 for CoRe: An Efficient Coarse-refined Training Framework for BERT
Figure 2 for CoRe: An Efficient Coarse-refined Training Framework for BERT
Figure 3 for CoRe: An Efficient Coarse-refined Training Framework for BERT
Figure 4 for CoRe: An Efficient Coarse-refined Training Framework for BERT

  Access Paper or Ask Questions

Deep Neural Networks with Short Circuits for Improved Gradient Learning


Sep 23, 2020
Ming Yan, Xueli Xiao, Joey Tianyi Zhou, Yi Pan

Figure 1 for Deep Neural Networks with Short Circuits for Improved Gradient Learning
Figure 2 for Deep Neural Networks with Short Circuits for Improved Gradient Learning
Figure 3 for Deep Neural Networks with Short Circuits for Improved Gradient Learning
Figure 4 for Deep Neural Networks with Short Circuits for Improved Gradient Learning

  Access Paper or Ask Questions

Fast algorithms for robust principal component analysis with an upper bound on the rank


Sep 03, 2020
Ningyu Sha, Lei Shi, Ming Yan

Figure 1 for Fast algorithms for robust principal component analysis with an upper bound on the rank
Figure 2 for Fast algorithms for robust principal component analysis with an upper bound on the rank
Figure 3 for Fast algorithms for robust principal component analysis with an upper bound on the rank
Figure 4 for Fast algorithms for robust principal component analysis with an upper bound on the rank
* Accepted by Inverse Problems and Imaging 
  Access Paper or Ask Questions

Linear Convergent Decentralized Optimization with Compression


Jul 01, 2020
Xiaorui Liu, Yao Li, Rongrong Wang, Jiliang Tang, Ming Yan

Figure 1 for Linear Convergent Decentralized Optimization with Compression
Figure 2 for Linear Convergent Decentralized Optimization with Compression
Figure 3 for Linear Convergent Decentralized Optimization with Compression
Figure 4 for Linear Convergent Decentralized Optimization with Compression

  Access Paper or Ask Questions

Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm


Jun 23, 2020
Xueli Xiao, Ming Yan, Sunitha Basodi, Chunyan Ji, Yi Pan

Figure 1 for Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm
Figure 2 for Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm
Figure 3 for Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm
Figure 4 for Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm

  Access Paper or Ask Questions

A Multi-Agent Primal-Dual Strategy for Composite Optimization over Distributed Features


Jun 15, 2020
Sulaiman A. Alghunaim, Ming Yan, Ali H. Sayed

Figure 1 for A Multi-Agent Primal-Dual Strategy for Composite Optimization over Distributed Features
* To appear in European Signal Processing Conference (EUSIPCO) 2020 
  Access Paper or Ask Questions

PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation


Apr 14, 2020
Bin Bi, Chenliang Li, Chen Wu, Ming Yan, Wei Wang

Figure 1 for PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
Figure 2 for PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
Figure 3 for PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
Figure 4 for PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
* arXiv admin note: text overlap with arXiv:1910.10683, arXiv:1910.13461 by other authors 
  Access Paper or Ask Questions

Manifold Denoising by Nonlinear Robust Principal Component Analysis


Nov 10, 2019
He Lyu, Ningyu Sha, Shuyang Qin, Ming Yan, Yuying Xie, Rongrong Wang

Figure 1 for Manifold Denoising by Nonlinear Robust Principal Component Analysis
Figure 2 for Manifold Denoising by Nonlinear Robust Principal Component Analysis
Figure 3 for Manifold Denoising by Nonlinear Robust Principal Component Analysis
Figure 4 for Manifold Denoising by Nonlinear Robust Principal Component Analysis

  Access Paper or Ask Questions

A Double Residual Compression Algorithm for Efficient Distributed Learning


Oct 16, 2019
Xiaorui Liu, Yao Li, Jiliang Tang, Ming Yan

Figure 1 for A Double Residual Compression Algorithm for Efficient Distributed Learning
Figure 2 for A Double Residual Compression Algorithm for Efficient Distributed Learning
Figure 3 for A Double Residual Compression Algorithm for Efficient Distributed Learning
Figure 4 for A Double Residual Compression Algorithm for Efficient Distributed Learning

  Access Paper or Ask Questions

Symmetric Regularization based BERT for Pair-wise Semantic Reasoning


Sep 08, 2019
Xingyi Cheng, Weidi Xu, Kunlong Chen, Wei Wang, Bin Bi, Ming Yan, Chen Wu, Luo Si, Wei Chu, Taifeng Wang

Figure 1 for Symmetric Regularization based BERT for Pair-wise Semantic Reasoning
Figure 2 for Symmetric Regularization based BERT for Pair-wise Semantic Reasoning
Figure 3 for Symmetric Regularization based BERT for Pair-wise Semantic Reasoning
Figure 4 for Symmetric Regularization based BERT for Pair-wise Semantic Reasoning
* 8 pages, 3 figures, 6 tables 
  Access Paper or Ask Questions

Incorporating External Knowledge into Machine Reading for Generative Question Answering


Sep 06, 2019
Bin Bi, Chen Wu, Ming Yan, Wei Wang, Jiangnan Xia, Chenliang Li

Figure 1 for Incorporating External Knowledge into Machine Reading for Generative Question Answering
Figure 2 for Incorporating External Knowledge into Machine Reading for Generative Question Answering
Figure 3 for Incorporating External Knowledge into Machine Reading for Generative Question Answering
Figure 4 for Incorporating External Knowledge into Machine Reading for Generative Question Answering
* Accepted at EMNLP 2019 
  Access Paper or Ask Questions

Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning


Sep 05, 2019
Jiangnan Xia, Chen Wu, Ming Yan

Figure 1 for Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning
Figure 2 for Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning
Figure 3 for Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning
Figure 4 for Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning
* Accepted at CIKM'19, 4 pages 
  Access Paper or Ask Questions

StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding


Aug 16, 2019
Wei Wang, Bin Bi, Ming Yan, Chen Wu, Zuyi Bao, Liwei Peng, Luo Si

Figure 1 for StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
Figure 2 for StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
Figure 3 for StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
Figure 4 for StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
* 10 Pages 
  Access Paper or Ask Questions

On linear convergence of two decentralized algorithms


Jun 17, 2019
Yao Li, Ming Yan

Figure 1 for On linear convergence of two decentralized algorithms
Figure 2 for On linear convergence of two decentralized algorithms
Figure 3 for On linear convergence of two decentralized algorithms

  Access Paper or Ask Questions

Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering


Nov 29, 2018
Wei Wang, Ming Yan, Chen Wu

Figure 1 for Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering
Figure 2 for Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering
Figure 3 for Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering
Figure 4 for Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering
* Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 1705-1714 
  Access Paper or Ask Questions

A Deep Cascade Model for Multi-Document Reading Comprehension


Nov 28, 2018
Ming Yan, Jiangnan Xia, Chen Wu, Bin Bi, Zhongzhou Zhao, Ji Zhang, Luo Si, Rui Wang, Wei Wang, Haiqing Chen

Figure 1 for A Deep Cascade Model for Multi-Document Reading Comprehension
Figure 2 for A Deep Cascade Model for Multi-Document Reading Comprehension
Figure 3 for A Deep Cascade Model for Multi-Document Reading Comprehension
Figure 4 for A Deep Cascade Model for Multi-Document Reading Comprehension
* Accepted at AAAI 2019 
  Access Paper or Ask Questions

Fast Signal Recovery from Saturated Measurements by Linear Loss and Nonconvex Penalties


Sep 12, 2018
Fan He, Xiaolin Huang, Yipeng Liu, Ming Yan

Figure 1 for Fast Signal Recovery from Saturated Measurements by Linear Loss and Nonconvex Penalties
Figure 2 for Fast Signal Recovery from Saturated Measurements by Linear Loss and Nonconvex Penalties
Figure 3 for Fast Signal Recovery from Saturated Measurements by Linear Loss and Nonconvex Penalties
Figure 4 for Fast Signal Recovery from Saturated Measurements by Linear Loss and Nonconvex Penalties

  Access Paper or Ask Questions

D$^2$: Decentralized Training over Decentralized Data


Apr 20, 2018
Hanlin Tang, Xiangru Lian, Ming Yan, Ce Zhang, Ji Liu

Figure 1 for D$^2$: Decentralized Training over Decentralized Data
Figure 2 for D$^2$: Decentralized Training over Decentralized Data

  Access Paper or Ask Questions

Pinball Loss Minimization for One-bit Compressive Sensing: Convex Models and Algorithms


Mar 19, 2018
Xiaolin Huang, Lei Shi, Ming Yan, Johan A. K. Suykens

Figure 1 for Pinball Loss Minimization for One-bit Compressive Sensing: Convex Models and Algorithms
Figure 2 for Pinball Loss Minimization for One-bit Compressive Sensing: Convex Models and Algorithms
Figure 3 for Pinball Loss Minimization for One-bit Compressive Sensing: Convex Models and Algorithms
Figure 4 for Pinball Loss Minimization for One-bit Compressive Sensing: Convex Models and Algorithms
* 11 pages 
  Access Paper or Ask Questions

A new primal-dual algorithm for minimizing the sum of three functions with a linear operator


Jan 29, 2018
Ming Yan

Figure 1 for A new primal-dual algorithm for minimizing the sum of three functions with a linear operator
* v2 added the ergodic and nonergodic convergence rates for the primal-dual gap; v3 added the infimal convolution result and changed the title; v4 modifies the primal-dual gap and add more recent references 
  Access Paper or Ask Questions