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 Sijia Liu

Sijia Liu

Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks


Oct 12, 2021
Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong

Figure 1 for Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
Figure 2 for Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
Figure 3 for Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
Figure 4 for Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
* Thirty-fifth Conference on Neural Information Processing Systems, 2021 
  Access Paper or Ask Questions

Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD


Sep 15, 2021
Chen Fan, Parikshit Ram, Sijia Liu

Figure 1 for Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
Figure 2 for Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
Figure 3 for Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
Figure 4 for Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD

  Access Paper or Ask Questions

Certifiably Robust Interpretation via Renyi Differential Privacy


Jul 04, 2021
Ao Liu, Xiaoyu Chen, Sijia Liu, Lirong Xia, Chuang Gan

Figure 1 for Certifiably Robust Interpretation via Renyi Differential Privacy
Figure 2 for Certifiably Robust Interpretation via Renyi Differential Privacy
Figure 3 for Certifiably Robust Interpretation via Renyi Differential Privacy
Figure 4 for Certifiably Robust Interpretation via Renyi Differential Privacy
* 19 page main text + appendix 
  Access Paper or Ask Questions

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?


Jul 01, 2021
Xiaolong Ma, Geng Yuan, Xuan Shen, Tianlong Chen, Xuxi Chen, Xiaohan Chen, Ning Liu, Minghai Qin, Sijia Liu, Zhangyang Wang, Yanzhi Wang

Figure 1 for Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Figure 2 for Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Figure 3 for Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Figure 4 for Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

  Access Paper or Ask Questions

ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense


Jun 27, 2021
Ren Wang, Tianqi Chen, Philip Yao, Sijia Liu, Indika Rajapakse, Alfred Hero

Figure 1 for ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense
Figure 2 for ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense
Figure 3 for ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense
Figure 4 for ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense

  Access Paper or Ask Questions

A Compression-Compilation Framework for On-mobile Real-time BERT Applications


Jun 06, 2021
Wei Niu, Zhenglun Kong, Geng Yuan, Weiwen Jiang, Jiexiong Guan, Caiwen Ding, Pu Zhao, Sijia Liu, Bin Ren, Yanzhi Wang

Figure 1 for A Compression-Compilation Framework for On-mobile Real-time BERT Applications
Figure 2 for A Compression-Compilation Framework for On-mobile Real-time BERT Applications
Figure 3 for A Compression-Compilation Framework for On-mobile Real-time BERT Applications
Figure 4 for A Compression-Compilation Framework for On-mobile Real-time BERT Applications
* arXiv admin note: substantial text overlap with arXiv:2009.06823 
  Access Paper or Ask Questions

Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors


Apr 28, 2021
Zhuoyun Li, Changhong Zhong, Sijia Liu, Ruixuan Wang, Wei-Shi Zheng

Figure 1 for Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors
Figure 2 for Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors
Figure 3 for Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors
Figure 4 for Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractors

  Access Paper or Ask Questions

Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation


Mar 25, 2021
Yi Sun, Abel Valente, Sijia Liu, Dakuo Wang

Figure 1 for Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
Figure 2 for Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
Figure 3 for Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
Figure 4 for Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation

  Access Paper or Ask Questions

Generating Adversarial Computer Programs using Optimized Obfuscations


Mar 18, 2021
Shashank Srikant, Sijia Liu, Tamara Mitrovska, Shiyu Chang, Quanfu Fan, Gaoyuan Zhang, Una-May O'Reilly

Figure 1 for Generating Adversarial Computer Programs using Optimized Obfuscations
Figure 2 for Generating Adversarial Computer Programs using Optimized Obfuscations
Figure 3 for Generating Adversarial Computer Programs using Optimized Obfuscations
Figure 4 for Generating Adversarial Computer Programs using Optimized Obfuscations
* This work will be published at ICLR 2021 
  Access Paper or Ask Questions

On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations


Feb 25, 2021
Chi Zhang, Jinghan Jia, Burhaneddin Yaman, Steen Moeller, Sijia Liu, Mingyi Hong, Mehmet Akçakaya

Figure 1 for On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
Figure 2 for On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
Figure 3 for On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
Figure 4 for On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
* To appear in Proceedings of the 29th Annual Meeting of ISMRM, 2021 
  Access Paper or Ask Questions

On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning


Feb 20, 2021
Ren Wang, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Chuang Gan, Meng Wang

Figure 1 for On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Figure 2 for On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Figure 3 for On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Figure 4 for On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning

  Access Paper or Ask Questions

Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?


Feb 19, 2021
Ning Liu, Geng Yuan, Zhengping Che, Xuan Shen, Xiaolong Ma, Qing Jin, Jian Ren, Jian Tang, Sijia Liu, Yanzhi Wang

Figure 1 for Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?
Figure 2 for Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?
Figure 3 for Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?
Figure 4 for Lottery Ticket Implies Accuracy Degradation, Is It a Desirable Phenomenon?

  Access Paper or Ask Questions

Fast Training of Provably Robust Neural Networks by SingleProp


Feb 01, 2021
Akhilan Boopathy, Tsui-Wei Weng, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang, Luca Daniel

Figure 1 for Fast Training of Provably Robust Neural Networks by SingleProp
Figure 2 for Fast Training of Provably Robust Neural Networks by SingleProp
Figure 3 for Fast Training of Provably Robust Neural Networks by SingleProp
Figure 4 for Fast Training of Provably Robust Neural Networks by SingleProp
* Published at AAAI 2021 
  Access Paper or Ask Questions

Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device


Dec 26, 2020
Pu Zhao, Wei Niu, Geng Yuan, Yuxuan Cai, Hsin-Hsuan Sung, Wujie Wen, Sijia Liu, Xipeng Shen, Bin Ren, Yanzhi Wang, Xue Lin

Figure 1 for Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
Figure 2 for Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
Figure 3 for Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
Figure 4 for Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device

  Access Paper or Ask Questions

Self-Progressing Robust Training


Dec 22, 2020
Minhao Cheng, Pin-Yu Chen, Sijia Liu, Shiyu Chang, Cho-Jui Hsieh, Payel Das

Figure 1 for Self-Progressing Robust Training
Figure 2 for Self-Progressing Robust Training
Figure 3 for Self-Progressing Robust Training
Figure 4 for Self-Progressing Robust Training
* Accepted in AAAI2021 
  Access Paper or Ask Questions

Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework


Dec 21, 2020
Pranay Sharma, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Xue Lin, Pramod K. Varshney

Figure 1 for Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework
Figure 2 for Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework
Figure 3 for Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework
Figure 4 for Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework
* 27 pages, 3 figures 
  Access Paper or Ask Questions

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models


Dec 12, 2020
Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael Carbin, Zhangyang Wang

Figure 1 for The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Figure 2 for The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Figure 3 for The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Figure 4 for The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

  Access Paper or Ask Questions

6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration


Dec 01, 2020
Zhengang Li, Geng Yuan, Wei Niu, Yanyu Li, Pu Zhao, Yuxuan Cai, Xuan Shen, Zheng Zhan, Zhenglun Kong, Qing Jin, Zhiyu Chen, Sijia Liu, Kaiyuan Yang, Bin Ren, Yanzhi Wang, Xue Lin

Figure 1 for 6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
Figure 2 for 6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
Figure 3 for 6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
Figure 4 for 6.7ms on Mobile with over 78% ImageNet Accuracy: Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration

  Access Paper or Ask Questions

Learned Fine-Tuner for Incongruous Few-Shot Learning


Oct 20, 2020
Pu Zhao, Sijia Liu, Parikshit Ram, Songtao Lu, Djallel Bouneffouf, Xue Lin

Figure 1 for Learned Fine-Tuner for Incongruous Few-Shot Learning
Figure 2 for Learned Fine-Tuner for Incongruous Few-Shot Learning
Figure 3 for Learned Fine-Tuner for Incongruous Few-Shot Learning
Figure 4 for Learned Fine-Tuner for Incongruous Few-Shot Learning

  Access Paper or Ask Questions

Training Stronger Baselines for Learning to Optimize


Oct 18, 2020
Tianlong Chen, Weiyi Zhang, Jingyang Zhou, Shiyu Chang, Sijia Liu, Lisa Amini, Zhangyang Wang

Figure 1 for Training Stronger Baselines for Learning to Optimize
Figure 2 for Training Stronger Baselines for Learning to Optimize
Figure 3 for Training Stronger Baselines for Learning to Optimize
Figure 4 for Training Stronger Baselines for Learning to Optimize
* NeurIPS 2020 Spotlight Oral 
  Access Paper or Ask Questions

Higher-Order Certification for Randomized Smoothing


Oct 13, 2020
Jeet Mohapatra, Ching-Yun Ko, Tsui-Wei Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel

Figure 1 for Higher-Order Certification for Randomized Smoothing
Figure 2 for Higher-Order Certification for Randomized Smoothing
Figure 3 for Higher-Order Certification for Randomized Smoothing
Figure 4 for Higher-Order Certification for Randomized Smoothing
* Accepted to NeurIPS2020(spotlight) 
  Access Paper or Ask Questions

TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series


Oct 04, 2020
Yang Jiao, Kai Yang, Shaoyu Dou, Pan Luo, Sijia Liu, Dongjin Song

Figure 1 for TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series
Figure 2 for TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series
Figure 3 for TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series
Figure 4 for TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series

  Access Paper or Ask Questions

Achieving Real-Time Execution of Transformer-based Large-scale Models on Mobile with Compiler-aware Neural Architecture Optimization


Sep 15, 2020
Wei Niu, Zhenglun Kong, Geng Yuan, Weiwen Jiang, Jiexiong Guan, Caiwen Ding, Pu Zhao, Sijia Liu, Bin Ren, Yanzhi Wang

Figure 1 for Achieving Real-Time Execution of Transformer-based Large-scale Models on Mobile with Compiler-aware Neural Architecture Optimization
Figure 2 for Achieving Real-Time Execution of Transformer-based Large-scale Models on Mobile with Compiler-aware Neural Architecture Optimization
Figure 3 for Achieving Real-Time Execution of Transformer-based Large-scale Models on Mobile with Compiler-aware Neural Architecture Optimization
Figure 4 for Achieving Real-Time Execution of Transformer-based Large-scale Models on Mobile with Compiler-aware Neural Architecture Optimization

  Access Paper or Ask Questions

Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases


Jul 31, 2020
Ren Wang, Gaoyuan Zhang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong, Meng Wang

Figure 1 for Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
Figure 2 for Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
Figure 3 for Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
Figure 4 for Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases

  Access Paper or Ask Questions

The Lottery Ticket Hypothesis for Pre-trained BERT Networks


Jul 23, 2020
Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Zhangyang Wang, Michael Carbin


  Access Paper or Ask Questions

Solving Constrained CASH Problems with ADMM


Jul 11, 2020
Parikshit Ram, Sijia Liu, Deepak Vijaykeerthi, Dakuo Wang, Djallel Bouneffouf, Greg Bramble, Horst Samulowitz, Alexander G. Gray

Figure 1 for Solving Constrained CASH Problems with ADMM
Figure 2 for Solving Constrained CASH Problems with ADMM
Figure 3 for Solving Constrained CASH Problems with ADMM
Figure 4 for Solving Constrained CASH Problems with ADMM
* 7th ICML Workshop on Automated Machine Learning (2020) 
  Access Paper or Ask Questions

Proper Network Interpretability Helps Adversarial Robustness in Classification


Jun 26, 2020
Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang, Cynthia Liu, Pin-Yu Chen, Shiyu Chang, Luca Daniel

Figure 1 for Proper Network Interpretability Helps Adversarial Robustness in Classification
Figure 2 for Proper Network Interpretability Helps Adversarial Robustness in Classification
Figure 3 for Proper Network Interpretability Helps Adversarial Robustness in Classification
Figure 4 for Proper Network Interpretability Helps Adversarial Robustness in Classification
* 22 pages, 9 figures, Published at ICML 2020 
  Access Paper or Ask Questions

Can 3D Adversarial Logos Cloak Humans?


Jun 25, 2020
Tianlong Chen, Yi Wang, Jingyang Zhou, Sijia Liu, Shiyu Chang, Chandrajit Bajaj, Zhangyang Wang

Figure 1 for Can 3D Adversarial Logos Cloak Humans?
Figure 2 for Can 3D Adversarial Logos Cloak Humans?
Figure 3 for Can 3D Adversarial Logos Cloak Humans?
Figure 4 for Can 3D Adversarial Logos Cloak Humans?

  Access Paper or Ask Questions