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 Liang Zhao

Liang Zhao

RefBERT: Compressing BERT by Referencing to Pre-computed Representations


Jun 11, 2021
Xinyi Wang, Haiqin Yang, Liang Zhao, Yang Mo, Jianping Shen

Figure 1 for RefBERT: Compressing BERT by Referencing to Pre-computed Representations
Figure 2 for RefBERT: Compressing BERT by Referencing to Pre-computed Representations
Figure 3 for RefBERT: Compressing BERT by Referencing to Pre-computed Representations
Figure 4 for RefBERT: Compressing BERT by Referencing to Pre-computed Representations
* 8 pages, 1 figure, 3 tables, in IJCNN'21 
  Access Paper or Ask Questions

Direct Simultaneous Multi-Image Registration


May 21, 2021
Zhehua Mao, Liang Zhao, Shoudong Huang, Yiting Fan, Alex Pui-Wai Lee

Figure 1 for Direct Simultaneous Multi-Image Registration
Figure 2 for Direct Simultaneous Multi-Image Registration
Figure 3 for Direct Simultaneous Multi-Image Registration
Figure 4 for Direct Simultaneous Multi-Image Registration
* 10 pages, 3 figures, 1 table 
  Access Paper or Ask Questions

Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework


May 20, 2021
Junxiang Wang, Hongyi Li, Zheng Chai, Yongchao Wang, Yue Cheng, Liang Zhao

Figure 1 for Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework
Figure 2 for Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework
Figure 3 for Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework
Figure 4 for Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework
* Junxiang Wang and Hongyi Li contribute equally to this work, and Yongchao Wang and Liang Zhao are corresponding authors. This work is under progress. arXiv admin note: substantial text overlap with arXiv:2009.02868 
  Access Paper or Ask Questions

Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning


May 05, 2021
Yuyang Gao, Giorgio A. Ascoli, Liang Zhao

Figure 1 for Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning
Figure 2 for Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning
Figure 3 for Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning
Figure 4 for Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning
* Under review at Neural Networks - Special Issue on AI and Brain Science 
  Access Paper or Ask Questions

Interpretable Distance Metric Learning for Handwritten Chinese Character Recognition


Mar 17, 2021
Boxiang Dong, Aparna S. Varde, Danilo Stevanovic, Jiayin Wang, Liang Zhao

Figure 1 for Interpretable Distance Metric Learning for Handwritten Chinese Character Recognition
Figure 2 for Interpretable Distance Metric Learning for Handwritten Chinese Character Recognition
Figure 3 for Interpretable Distance Metric Learning for Handwritten Chinese Character Recognition
Figure 4 for Interpretable Distance Metric Learning for Handwritten Chinese Character Recognition

  Access Paper or Ask Questions

Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss


Mar 17, 2021
Boxiang Dong, Hui, Wang, Aparna S. Varde, Dawei Li, Bharath K. Samanthula, Weifeng Sun, Liang Zhao

Figure 1 for Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss
Figure 2 for Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss
Figure 3 for Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss
Figure 4 for Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss

  Access Paper or Ask Questions

Sign-regularized Multi-task Learning


Feb 22, 2021
Johnny Torres, Guangji Bai, Junxiang Wang, Liang Zhao, Carmen Vaca, Cristina Abad

Figure 1 for Sign-regularized Multi-task Learning
Figure 2 for Sign-regularized Multi-task Learning
Figure 3 for Sign-regularized Multi-task Learning
Figure 4 for Sign-regularized Multi-task Learning
* 17 pages, 4 figures, v1 
  Access Paper or Ask Questions

GP: Context-free Grammar Pre-training for Text-to-SQL Parsers


Jan 25, 2021
Liang Zhao, Hexin Cao, Yunsong Zhao

Figure 1 for GP: Context-free Grammar Pre-training for Text-to-SQL Parsers
Figure 2 for GP: Context-free Grammar Pre-training for Text-to-SQL Parsers
Figure 3 for GP: Context-free Grammar Pre-training for Text-to-SQL Parsers
Figure 4 for GP: Context-free Grammar Pre-training for Text-to-SQL Parsers

  Access Paper or Ask Questions

Online Decision Trees with Fairness


Oct 15, 2020
Wenbin Zhang, Liang Zhao

Figure 1 for Online Decision Trees with Fairness
Figure 2 for Online Decision Trees with Fairness
Figure 3 for Online Decision Trees with Fairness
Figure 4 for Online Decision Trees with Fairness
* arXiv admin note: substantial text overlap with arXiv:1907.07237 
  Access Paper or Ask Questions

Disentangled Dynamic Graph Deep Generation


Oct 14, 2020
Wenbin Zhang, Liming Zhang, Dieter Pfoser, Liang Zhao

Figure 1 for Disentangled Dynamic Graph Deep Generation
Figure 2 for Disentangled Dynamic Graph Deep Generation
Figure 3 for Disentangled Dynamic Graph Deep Generation
Figure 4 for Disentangled Dynamic Graph Deep Generation

  Access Paper or Ask Questions

FedAT: A Communication-Efficient Federated Learning Method with Asynchronous Tiers under Non-IID Data


Oct 12, 2020
Zheng Chai, Yujing Chen, Liang Zhao, Yue Cheng, Huzefa Rangwala

Figure 1 for FedAT: A Communication-Efficient Federated Learning Method with Asynchronous Tiers under Non-IID Data
Figure 2 for FedAT: A Communication-Efficient Federated Learning Method with Asynchronous Tiers under Non-IID Data
Figure 3 for FedAT: A Communication-Efficient Federated Learning Method with Asynchronous Tiers under Non-IID Data
Figure 4 for FedAT: A Communication-Efficient Federated Learning Method with Asynchronous Tiers under Non-IID Data

  Access Paper or Ask Questions

A new network-base high-level data classification methodology (Quipus) by modeling attribute-attribute interactions


Sep 28, 2020
Esteban Wilfredo Vilca Zuñiga, Liang Zhao

Figure 1 for A new network-base high-level data classification methodology (Quipus) by modeling attribute-attribute interactions
Figure 2 for A new network-base high-level data classification methodology (Quipus) by modeling attribute-attribute interactions
Figure 3 for A new network-base high-level data classification methodology (Quipus) by modeling attribute-attribute interactions
Figure 4 for A new network-base high-level data classification methodology (Quipus) by modeling attribute-attribute interactions

  Access Paper or Ask Questions

Graph-based Multi-hop Reasoning for Long Text Generation


Sep 28, 2020
Liang Zhao, Jingjing Xu, Junyang Lin, Yichang Zhang, Hongxia Yang, Xu Sun

Figure 1 for Graph-based Multi-hop Reasoning for Long Text Generation
Figure 2 for Graph-based Multi-hop Reasoning for Long Text Generation
Figure 3 for Graph-based Multi-hop Reasoning for Long Text Generation
Figure 4 for Graph-based Multi-hop Reasoning for Long Text Generation

  Access Paper or Ask Questions

Factorized Deep Generative Models for Trajectory Generation with Spatiotemporal-Validity Constraints


Sep 20, 2020
Liming Zhang, Liang Zhao, Dieter Pfoser

Figure 1 for Factorized Deep Generative Models for Trajectory Generation with Spatiotemporal-Validity Constraints
Figure 2 for Factorized Deep Generative Models for Trajectory Generation with Spatiotemporal-Validity Constraints
Figure 3 for Factorized Deep Generative Models for Trajectory Generation with Spatiotemporal-Validity Constraints
Figure 4 for Factorized Deep Generative Models for Trajectory Generation with Spatiotemporal-Validity Constraints

  Access Paper or Ask Questions

A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality


Sep 16, 2020
Esteban Vilca, Liang Zhao

Figure 1 for A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality
Figure 2 for A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality
Figure 3 for A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality
Figure 4 for A Network-Based High-Level Data Classification Algorithm Using Betweenness Centrality

  Access Paper or Ask Questions

Tunable Subnetwork Splitting for Model-parallelism of Neural Network Training


Sep 16, 2020
Junxiang Wang, Zheng Chai, Yue Cheng, Liang Zhao

Figure 1 for Tunable Subnetwork Splitting for Model-parallelism of Neural Network Training
Figure 2 for Tunable Subnetwork Splitting for Model-parallelism of Neural Network Training
Figure 3 for Tunable Subnetwork Splitting for Model-parallelism of Neural Network Training
* ICML 2020 Workshop on "Beyond first-order methods in ML systems" 
  Access Paper or Ask Questions

Event Prediction in the Big Data Era: A Systematic Survey


Aug 04, 2020
Liang Zhao

Figure 1 for Event Prediction in the Big Data Era: A Systematic Survey
Figure 2 for Event Prediction in the Big Data Era: A Systematic Survey
Figure 3 for Event Prediction in the Big Data Era: A Systematic Survey
Figure 4 for Event Prediction in the Big Data Era: A Systematic Survey

  Access Paper or Ask Questions

Event Prediction in Big Data Era: A Systematic Survey


Jul 21, 2020
Liang Zhao

Figure 1 for Event Prediction in Big Data Era: A Systematic Survey
Figure 2 for Event Prediction in Big Data Era: A Systematic Survey
Figure 3 for Event Prediction in Big Data Era: A Systematic Survey
Figure 4 for Event Prediction in Big Data Era: A Systematic Survey

  Access Paper or Ask Questions

A Systematic Survey on Deep Generative Models for Graph Generation


Jul 18, 2020
Xiaojie Guo, Liang Zhao

Figure 1 for A Systematic Survey on Deep Generative Models for Graph Generation
Figure 2 for A Systematic Survey on Deep Generative Models for Graph Generation
Figure 3 for A Systematic Survey on Deep Generative Models for Graph Generation
Figure 4 for A Systematic Survey on Deep Generative Models for Graph Generation

  Access Paper or Ask Questions

TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models


Jun 09, 2020
Liming Zhang, Liang Zhao, Shan Qin, Dieter Pfoser

Figure 1 for TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models
Figure 2 for TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models
Figure 3 for TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models
Figure 4 for TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models

  Access Paper or Ask Questions

Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement


Jun 09, 2020
Xiaojie Guo, Liang Zhao, Zhao Qin, Lingfei Wu, Amarda Shehu, Yanfang Ye

Figure 1 for Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement
Figure 2 for Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement
Figure 3 for Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement
Figure 4 for Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement
* This paper has been accepted by KDD 2020 
  Access Paper or Ask Questions

TG-GAN: Deep Generative Models for Continuously-time Temporal Graph Generation


May 17, 2020
Liming Zhang, Liang Zhao, Shan Qin, Dieter Pfoser

Figure 1 for TG-GAN: Deep Generative Models for Continuously-time Temporal Graph Generation
Figure 2 for TG-GAN: Deep Generative Models for Continuously-time Temporal Graph Generation
Figure 3 for TG-GAN: Deep Generative Models for Continuously-time Temporal Graph Generation
Figure 4 for TG-GAN: Deep Generative Models for Continuously-time Temporal Graph Generation

  Access Paper or Ask Questions

Chronnet: a network-based model for spatiotemporal data analysis


Apr 23, 2020
Leonardo N. Ferreira, Didier A. Vega-Oliveros, Moshe Cotacallapa, Manoel F. Cardoso, Marcos G. Quiles, Liang Zhao, Elbert E. N. Macau

Figure 1 for Chronnet: a network-based model for spatiotemporal data analysis
Figure 2 for Chronnet: a network-based model for spatiotemporal data analysis
Figure 3 for Chronnet: a network-based model for spatiotemporal data analysis
Figure 4 for Chronnet: a network-based model for spatiotemporal data analysis

  Access Paper or Ask Questions

Generating Tertiary Protein Structures via an Interpretative Variational Autoencoder


Apr 08, 2020
Xiaojie Guo, Sivani Tadepalli, Liang Zhao, Amarda Shehu

Figure 1 for Generating Tertiary Protein Structures via an Interpretative Variational Autoencoder
Figure 2 for Generating Tertiary Protein Structures via an Interpretative Variational Autoencoder
Figure 3 for Generating Tertiary Protein Structures via an Interpretative Variational Autoencoder
Figure 4 for Generating Tertiary Protein Structures via an Interpretative Variational Autoencoder

  Access Paper or Ask Questions

Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery


Mar 22, 2020
Jingwei Song, Jun Wang, Liang Zhao, Shoudong Huang, Gamini Dissanayake

Figure 1 for Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery
Figure 2 for Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery
Figure 3 for Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery
Figure 4 for Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery
* Published in IROS2017 ()2017 IEEE/RSJ International Conference on Intelligent Robots and Systems. arXiv admin note: text overlap with arXiv:1803.02009 
  Access Paper or Ask Questions

Deep Multi-attributed Graph Translation with Node-Edge Co-evolution


Mar 22, 2020
Xiaojie Guo, Liang Zhao, Cameron Nowzari, Setareh Rafatirad, Houman Homayoun, Sai Manoj Pudukotai Dinakarrao

Figure 1 for Deep Multi-attributed Graph Translation with Node-Edge Co-evolution
Figure 2 for Deep Multi-attributed Graph Translation with Node-Edge Co-evolution
Figure 3 for Deep Multi-attributed Graph Translation with Node-Edge Co-evolution
Figure 4 for Deep Multi-attributed Graph Translation with Node-Edge Co-evolution
* International Conference on Data Mining (ICDM), Beijing, China, 2019, pp. 250-259 
 * This paper has been accepted by International Conference on Data Mining (ICDM), Beijing, China, 2019 
  Access Paper or Ask Questions

Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks


Mar 01, 2020
Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Chang-Tien Lu

Figure 1 for Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks

  Access Paper or Ask Questions