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 Dongsheng Li

Dongsheng Li

EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks


Oct 18, 2021
Shengwei Li, Zhiquan Lai, Dongsheng Li, Xiangyu Ye, Yabo Duan

Figure 1 for EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks
Figure 2 for EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks
Figure 3 for EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks
Figure 4 for EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks

  Access Paper or Ask Questions

Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization


Oct 18, 2021
Tao Sun, Huaming Ling, Zuoqiang Shi, Dongsheng Li, Bao Wang

Figure 1 for Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
Figure 2 for Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
Figure 3 for Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
Figure 4 for Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization

  Access Paper or Ask Questions

S2 Reducer: High-Performance Sparse Communication to Accelerate Distributed Deep Learning


Oct 05, 2021
Keshi Ge, Yongquan Fu, Zhiquan Lai, Xiaoge Deng, Dongsheng Li

Figure 1 for S2 Reducer: High-Performance Sparse Communication to Accelerate Distributed Deep Learning
Figure 2 for S2 Reducer: High-Performance Sparse Communication to Accelerate Distributed Deep Learning
Figure 3 for S2 Reducer: High-Performance Sparse Communication to Accelerate Distributed Deep Learning
Figure 4 for S2 Reducer: High-Performance Sparse Communication to Accelerate Distributed Deep Learning
* 8 pages 
  Access Paper or Ask Questions

Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision


Aug 30, 2021
Bo Li, Xinyang Jiang, Donglin Bai, Yuge Zhang, Ningxin Zheng, Xuanyi Dong, Lu Liu, Yuqing Yang, Dongsheng Li

Figure 1 for Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
Figure 2 for Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
Figure 3 for Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
Figure 4 for Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
* ArXiv Preprint 
  Access Paper or Ask Questions

How Powerful is Graph Convolution for Recommendation?


Aug 17, 2021
Yifei Shen, Yongji Wu, Yao Zhang, Caihua Shan, Jun Zhang, Khaled B. Letaief, Dongsheng Li

Figure 1 for How Powerful is Graph Convolution for Recommendation?
Figure 2 for How Powerful is Graph Convolution for Recommendation?
Figure 3 for How Powerful is Graph Convolution for Recommendation?
Figure 4 for How Powerful is Graph Convolution for Recommendation?

  Access Paper or Ask Questions

Energy-Based Open-World Uncertainty Modeling for Confidence Calibration


Aug 16, 2021
Yezhen Wang, Bo Li, Tong Che, Kaiyang Zhou, Ziwei Liu, Dongsheng Li

Figure 1 for Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
Figure 2 for Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
Figure 3 for Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
Figure 4 for Energy-Based Open-World Uncertainty Modeling for Confidence Calibration
* ICCV 2021 (Poster) 
  Access Paper or Ask Questions

Invariant Information Bottleneck for Domain Generalization


Jun 14, 2021
Bo Li, Yifei Shen, Yezhen Wang, Wenzhen Zhu, Colorado J. Reed, Jun Zhang, Dongsheng Li, Kurt Keutzer, Han Zhao

Figure 1 for Invariant Information Bottleneck for Domain Generalization
Figure 2 for Invariant Information Bottleneck for Domain Generalization
Figure 3 for Invariant Information Bottleneck for Domain Generalization
Figure 4 for Invariant Information Bottleneck for Domain Generalization
* The work is in progress 
  Access Paper or Ask Questions

Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment


Jun 09, 2021
Baoyun Peng, Min Liu, Heng Yang, Zhaoning Zhang, Dongsheng Li

Figure 1 for Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
Figure 2 for Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
Figure 3 for Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
Figure 4 for Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment

  Access Paper or Ask Questions

Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation


Jun 07, 2021
Sanshi Yu, Zhuoxuan Jiang, Dong-Dong Chen, Shanshan Feng, Dongsheng Li, Qi Liu, Jinfeng Yi

Figure 1 for Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
Figure 2 for Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
Figure 3 for Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
Figure 4 for Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
* To appear in KDD'21 ADS 
  Access Paper or Ask Questions

Graph Pooling via Coarsened Graph Infomax


May 31, 2021
Yunsheng Pang, Yunxiang Zhao, Dongsheng Li

Figure 1 for Graph Pooling via Coarsened Graph Infomax
Figure 2 for Graph Pooling via Coarsened Graph Infomax
Figure 3 for Graph Pooling via Coarsened Graph Infomax
Figure 4 for Graph Pooling via Coarsened Graph Infomax

  Access Paper or Ask Questions

A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline


May 02, 2021
Yingying Zhao, Mingzhi Dong, Yujiang Wang, Da Feng, Qin Lv, Robert P. Dick, Dongsheng Li, Tun Lu, Ning Gu, Li Shang

Figure 1 for A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline
Figure 2 for A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline
Figure 3 for A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline
Figure 4 for A Reinforcement-Learning-Based Energy-Efficient Framework for Multi-Task Video Analytics Pipeline
* IEEE Transactions on Multimedia 
  Access Paper or Ask Questions

Decentralized Federated Averaging


Apr 23, 2021
Tao Sun, Dongsheng Li, Bao Wang

Figure 1 for Decentralized Federated Averaging
Figure 2 for Decentralized Federated Averaging
Figure 3 for Decentralized Federated Averaging
Figure 4 for Decentralized Federated Averaging

  Access Paper or Ask Questions

NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering


Apr 15, 2021
Dongsheng Li, Haodong Liu, Chao Chen, Yingying Zhao, Stephen M. Chu, Bo Yang

Figure 1 for NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering
Figure 2 for NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering
Figure 3 for NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering
Figure 4 for NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering

  Access Paper or Ask Questions

Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning


Apr 13, 2021
Ning Liu, Songlei Jian, Dongsheng Li, Yiming Zhang, Zhiquan Lai, Hongzuo Xu

Figure 1 for Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning
Figure 2 for Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning
Figure 3 for Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning
Figure 4 for Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning

  Access Paper or Ask Questions

Decentralized Statistical Inference with Unrolled Graph Neural Networks


Apr 04, 2021
He Wang, Yifei Shen, Ziyuan Wang, Dongsheng Li, Jun Zhang, Khaled B. Letaief, Jie Lu

Figure 1 for Decentralized Statistical Inference with Unrolled Graph Neural Networks
Figure 2 for Decentralized Statistical Inference with Unrolled Graph Neural Networks
Figure 3 for Decentralized Statistical Inference with Unrolled Graph Neural Networks
Figure 4 for Decentralized Statistical Inference with Unrolled Graph Neural Networks

  Access Paper or Ask Questions

Stability and Generalization of the Decentralized Stochastic Gradient Descent


Feb 23, 2021
Tao Sun, Dongsheng Li, Bao Wang

Figure 1 for Stability and Generalization of the Decentralized Stochastic Gradient Descent
Figure 2 for Stability and Generalization of the Decentralized Stochastic Gradient Descent
Figure 3 for Stability and Generalization of the Decentralized Stochastic Gradient Descent
Figure 4 for Stability and Generalization of the Decentralized Stochastic Gradient Descent
* AAAI-2021 
  Access Paper or Ask Questions

Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training


Jan 30, 2021
Linbo Qiao, Tao Sun, Hengyue Pan, Dongsheng Li

Figure 1 for Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training
Figure 2 for Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training
Figure 3 for Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training
Figure 4 for Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training

  Access Paper or Ask Questions

Learning content and context with language bias for Visual Question Answering


Dec 21, 2020
Chao Yang, Su Feng, Dongsheng Li, Huawei Shen, Guoqing Wang, Bin Jiang

Figure 1 for Learning content and context with language bias for Visual Question Answering
Figure 2 for Learning content and context with language bias for Visual Question Answering
Figure 3 for Learning content and context with language bias for Visual Question Answering
Figure 4 for Learning content and context with language bias for Visual Question Answering

  Access Paper or Ask Questions

PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension


Dec 20, 2020
Chao Yang, Guoqing Wang, Dongsheng Li, Huawei Shen, Su Feng, Bin Jiang

Figure 1 for PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension
Figure 2 for PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension
Figure 3 for PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension
Figure 4 for PPGN: Phrase-Guided Proposal Generation Network For Referring Expression Comprehension

  Access Paper or Ask Questions

Meta-Learning for Neural Relation Classification with Distant Supervision


Oct 26, 2020
Zhenzhen Li, Jian-Yun Nie, Benyou Wang, Pan Du, Yuhan Zhang, Lixin Zou, Dongsheng Li

Figure 1 for Meta-Learning for Neural Relation Classification with Distant Supervision
Figure 2 for Meta-Learning for Neural Relation Classification with Distant Supervision
Figure 3 for Meta-Learning for Neural Relation Classification with Distant Supervision
Figure 4 for Meta-Learning for Neural Relation Classification with Distant Supervision
* In Proceedings of CIKM, pp. 815-824. 2020 
 * 10 pages, 7 figures; corrected one encoding error in CIKM pdf 
  Access Paper or Ask Questions

Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation


Oct 12, 2020
Bo Li, Yezhen Wang, Shanghang Zhang, Dongsheng Li, Trevor Darrell, Kurt Keutzer, Han Zhao

Figure 1 for Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
Figure 2 for Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
Figure 3 for Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
Figure 4 for Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
* Preprint 
  Access Paper or Ask Questions

Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning


Aug 07, 2020
Yiqin Yu, Xu Min, Shiwan Zhao, Jing Mei, Fei Wang, Dongsheng Li, Kenney Ng, Shaochun Li

Figure 1 for Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning
Figure 2 for Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning
Figure 3 for Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning
Figure 4 for Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning
* 7 pages, 2 figures 
  Access Paper or Ask Questions