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 Jianyu Wang

Jianyu Wang

Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer


Sep 16, 2021
Yae Jee Cho, Jianyu Wang, Tarun Chiruvolu, Gauri Joshi

Figure 1 for Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer
Figure 2 for Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer
Figure 3 for Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer
Figure 4 for Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer

  Access Paper or Ask Questions

A Field Guide to Federated Optimization


Jul 14, 2021
Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, Blaise Aguera y Arcas, Maruan Al-Shedivat, Galen Andrew, Salman Avestimehr, Katharine Daly, Deepesh Data, Suhas Diggavi, Hubert Eichner, Advait Gadhikar, Zachary Garrett, Antonious M. Girgis, Filip Hanzely, Andrew Hard, Chaoyang He, Samuel Horvath, Zhouyuan Huo, Alex Ingerman, Martin Jaggi, Tara Javidi, Peter Kairouz, Satyen Kale, Sai Praneeth Karimireddy, Jakub Konecny, Sanmi Koyejo, Tian Li, Luyang Liu, Mehryar Mohri, Hang Qi, Sashank J. Reddi, Peter Richtarik, Karan Singhal, Virginia Smith, Mahdi Soltanolkotabi, Weikang Song, Ananda Theertha Suresh, Sebastian U. Stich, Ameet Talwalkar, Hongyi Wang, Blake Woodworth, Shanshan Wu, Felix X. Yu, Honglin Yuan, Manzil Zaheer, Mi Zhang, Tong Zhang, Chunxiang Zheng, Chen Zhu, Wennan Zhu

Figure 1 for A Field Guide to Federated Optimization
Figure 2 for A Field Guide to Federated Optimization
Figure 3 for A Field Guide to Federated Optimization
Figure 4 for A Field Guide to Federated Optimization

  Access Paper or Ask Questions

DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering


Jul 10, 2021
Jianyu Wang, Bing-Kun Bao, Changsheng Xu

Figure 1 for DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
Figure 2 for DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
Figure 3 for DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
Figure 4 for DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
* IEEE Transactions on Multimedia 2021 
 * 12 pages, 12 figures 
  Access Paper or Ask Questions

Local Adaptivity in Federated Learning: Convergence and Consistency


Jun 04, 2021
Jianyu Wang, Zheng Xu, Zachary Garrett, Zachary Charles, Luyang Liu, Gauri Joshi

Figure 1 for Local Adaptivity in Federated Learning: Convergence and Consistency
Figure 2 for Local Adaptivity in Federated Learning: Convergence and Consistency
Figure 3 for Local Adaptivity in Federated Learning: Convergence and Consistency
Figure 4 for Local Adaptivity in Federated Learning: Convergence and Consistency

  Access Paper or Ask Questions

Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays


Apr 07, 2021
Shanzheng Guan, Shupei Liu, Junqi Chen, Wenbo Zhu, Shengqiang Li, Xu Tan, Ziye Yang, Menglong Xu, Yijiang Chen, Jianyu Wang, Xiao-Lei Zhang

Figure 1 for Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays
Figure 2 for Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays
Figure 3 for Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays
Figure 4 for Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays

  Access Paper or Ask Questions

Minimum-volume Multichannel Nonnegative matrix factorization for blind source separation


Jan 16, 2021
Jianyu Wang, Shanzheng Guan, Xiao-Lei Zhang

Figure 1 for Minimum-volume Multichannel Nonnegative matrix factorization for blind source separation
Figure 2 for Minimum-volume Multichannel Nonnegative matrix factorization for blind source separation
Figure 3 for Minimum-volume Multichannel Nonnegative matrix factorization for blind source separation
Figure 4 for Minimum-volume Multichannel Nonnegative matrix factorization for blind source separation

  Access Paper or Ask Questions

Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies


Oct 03, 2020
Yae Jee Cho, Jianyu Wang, Gauri Joshi

Figure 1 for Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies
Figure 2 for Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies
Figure 3 for Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies
Figure 4 for Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies

  Access Paper or Ask Questions

Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization


Jul 15, 2020
Jianyu Wang, Qinghua Liu, Hao Liang, Gauri Joshi, H. Vincent Poor

Figure 1 for Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
Figure 2 for Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
Figure 3 for Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
Figure 4 for Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization

  Access Paper or Ask Questions

Band-limited Soft Actor Critic Model


Jun 19, 2020
Miguel Campo, Zhengxing Chen, Luke Kung, Kittipat Virochsiri, Jianyu Wang

Figure 1 for Band-limited Soft Actor Critic Model
Figure 2 for Band-limited Soft Actor Critic Model
Figure 3 for Band-limited Soft Actor Critic Model
Figure 4 for Band-limited Soft Actor Critic Model
* 8 pages plus additional material 
  Access Paper or Ask Questions

Slow and Stale Gradients Can Win the Race


Mar 23, 2020
Sanghamitra Dutta, Jianyu Wang, Gauri Joshi

Figure 1 for Slow and Stale Gradients Can Win the Race
Figure 2 for Slow and Stale Gradients Can Win the Race
Figure 3 for Slow and Stale Gradients Can Win the Race
Figure 4 for Slow and Stale Gradients Can Win the Race
* Some of the results have appeared in AISTATS 2018. This is an extended version with additional results, in particular, an adaptive synchronicity strategy called AdaSync. arXiv admin note: substantial text overlap with arXiv:1803.01113 
  Access Paper or Ask Questions

Machine Learning on Volatile Instances


Mar 12, 2020
Xiaoxi Zhang, Jianyu Wang, Gauri Joshi, Carlee Joe-Wong

Figure 1 for Machine Learning on Volatile Instances
Figure 2 for Machine Learning on Volatile Instances
Figure 3 for Machine Learning on Volatile Instances
Figure 4 for Machine Learning on Volatile Instances

  Access Paper or Ask Questions

Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD


Feb 21, 2020
Jianyu Wang, Hao Liang, Gauri Joshi

Figure 1 for Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD
Figure 2 for Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD
Figure 3 for Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD
Figure 4 for Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD
* Accepted to ICASSP 2020 
  Access Paper or Ask Questions

Advances and Open Problems in Federated Learning


Dec 10, 2019
Peter Kairouz, H. Brendan McMahan, Brendan Avent, AurΓ©lien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, AdriΓ  GascΓ³n, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub KonečnΓ½, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, TancrΓ¨de Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Γ–zgΓΌr, Rasmus Pagh, Mariana Raykova, Hang Qi, Daniel Ramage, Ramesh Raskar, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian TramΓ¨r, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao

Figure 1 for Advances and Open Problems in Federated Learning
Figure 2 for Advances and Open Problems in Federated Learning
Figure 3 for Advances and Open Problems in Federated Learning
Figure 4 for Advances and Open Problems in Federated Learning

  Access Paper or Ask Questions

Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction


Nov 22, 2019
Yantao Lu, Yunhan Jia, Jianyu Wang, Bai Li, Weiheng Chai, Lawrence Carin, Senem Velipasalar

Figure 1 for Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction
Figure 2 for Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction
Figure 3 for Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction
Figure 4 for Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction
* arXiv admin note: substantial text overlap with arXiv:1905.03333 
  Access Paper or Ask Questions

Deep topic modeling by multilayer bootstrap network and lasso


Oct 24, 2019
Jianyu Wang, Xiao-Lei Zhang

Figure 1 for Deep topic modeling by multilayer bootstrap network and lasso
Figure 2 for Deep topic modeling by multilayer bootstrap network and lasso
Figure 3 for Deep topic modeling by multilayer bootstrap network and lasso
Figure 4 for Deep topic modeling by multilayer bootstrap network and lasso

  Access Paper or Ask Questions

Compositional Generalization for Primitive Substitutions


Oct 07, 2019
Yuanpeng Li, Liang Zhao, Jianyu Wang, Joel Hestness

Figure 1 for Compositional Generalization for Primitive Substitutions
Figure 2 for Compositional Generalization for Primitive Substitutions
Figure 3 for Compositional Generalization for Primitive Substitutions
Figure 4 for Compositional Generalization for Primitive Substitutions
* EMNLP 2019 
  Access Paper or Ask Questions

SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum


Oct 01, 2019
Jianyu Wang, Vinayak Tantia, Nicolas Ballas, Michael Rabbat

Figure 1 for SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
Figure 2 for SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
Figure 3 for SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
Figure 4 for SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum

  Access Paper or Ask Questions

Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks


Jul 31, 2019
Haichao Zhang, Jianyu Wang

Figure 1 for Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks
Figure 2 for Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks
Figure 3 for Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks
Figure 4 for Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks

  Access Paper or Ask Questions

Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training


Jul 29, 2019
Haichao Zhang, Jianyu Wang

Figure 1 for Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
Figure 2 for Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
Figure 3 for Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
Figure 4 for Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training

  Access Paper or Ask Questions

Towards Adversarially Robust Object Detection


Jul 24, 2019
Haichao Zhang, Jianyu Wang

Figure 1 for Towards Adversarially Robust Object Detection
Figure 2 for Towards Adversarially Robust Object Detection
Figure 3 for Towards Adversarially Robust Object Detection
Figure 4 for Towards Adversarially Robust Object Detection
* ICCV 2019 
  Access Paper or Ask Questions

MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling


May 23, 2019
Jianyu Wang, Anit Kumar Sahu, Zhouyi Yang, Gauri Joshi, Soummya Kar

Figure 1 for MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling
Figure 2 for MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling
Figure 3 for MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling
Figure 4 for MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling

  Access Paper or Ask Questions

Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks


Nov 26, 2018
Jianyu Wang

Figure 1 for Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks
Figure 2 for Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks
Figure 3 for Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks
Figure 4 for Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks

  Access Paper or Ask Questions

Zero-Shot Transfer VQA Dataset


Nov 02, 2018
Yuanpeng Li, Yi Yang, Jianyu Wang, Wei Xu

Figure 1 for Zero-Shot Transfer VQA Dataset
Figure 2 for Zero-Shot Transfer VQA Dataset
Figure 3 for Zero-Shot Transfer VQA Dataset
Figure 4 for Zero-Shot Transfer VQA Dataset

  Access Paper or Ask Questions

Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms


Oct 19, 2018
Jianyu Wang, Gauri Joshi

Figure 1 for Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
Figure 2 for Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
Figure 3 for Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
Figure 4 for Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms

  Access Paper or Ask Questions

Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD


Oct 19, 2018
Jianyu Wang, Gauri Joshi

Figure 1 for Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD
Figure 2 for Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD
Figure 3 for Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD
Figure 4 for Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD

  Access Paper or Ask Questions

Improving Transferability of Adversarial Examples with Input Diversity


Jun 11, 2018
Cihang Xie, Zhishuai Zhang, Jianyu Wang, Yuyin Zhou, Zhou Ren, Alan Yuille

Figure 1 for Improving Transferability of Adversarial Examples with Input Diversity
Figure 2 for Improving Transferability of Adversarial Examples with Input Diversity
Figure 3 for Improving Transferability of Adversarial Examples with Input Diversity
Figure 4 for Improving Transferability of Adversarial Examples with Input Diversity
* Submitted to ECCV 2018, code available at https://github.com/cihangxie/DI-2-FGSM 
  Access Paper or Ask Questions

Adversarial Attacks and Defences Competition


Mar 31, 2018
Alexey Kurakin, Ian Goodfellow, Samy Bengio, Yinpeng Dong, Fangzhou Liao, Ming Liang, Tianyu Pang, Jun Zhu, Xiaolin Hu, Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren, Alan Yuille, Sangxia Huang, Yao Zhao, Yuzhe Zhao, Zhonglin Han, Junjiajia Long, Yerkebulan Berdibekov, Takuya Akiba, Seiya Tokui, Motoki Abe

Figure 1 for Adversarial Attacks and Defences Competition
Figure 2 for Adversarial Attacks and Defences Competition
Figure 3 for Adversarial Attacks and Defences Competition
Figure 4 for Adversarial Attacks and Defences Competition
* 36 pages, 10 figures 
  Access Paper or Ask Questions