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 Hongyuan Zha

Influence Estimation and Maximization via Neural Mean-Field Dynamics


Jun 03, 2021
Shushan He, Hongyuan Zha, Xiaojing Ye

* 26 pages, 6 figures. arXiv admin note: text overlap with arXiv:2006.09449 

  Access Paper or Ask Questions

Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach


May 18, 2021
Yan Li, Lingxiao Wang, Jiachen Yang, Ethan Wang, Zhaoran Wang, Tuo Zhao, Hongyuan Zha


  Access Paper or Ask Questions

Theoretical Study of Random Noise Defense against Query-Based Black-Box Attacks


Apr 23, 2021
Zeyu Qin, Yanbo Fan, Hongyuan Zha, Baoyuan Wu


  Access Paper or Ask Questions

Graph-Based Tri-Attention Network for Answer Ranking in CQA


Mar 20, 2021
Wei Zhang, Zeyuan Chen, Chao Dong, Wen Wang, Hongyuan Zha, Jianyong Wang

* 9 pages (published in AAAI 2021) 

  Access Paper or Ask Questions

Mean Field Game GAN


Mar 14, 2021
Shaojun Ma, Haomin Zhou, Hongyuan Zha


  Access Paper or Ask Questions

Reinforcement Learning for Adaptive Mesh Refinement


Mar 01, 2021
Jiachen Yang, Tarik Dzanic, Brenden Petersen, Jun Kudo, Ketan Mittal, Vladimir Tomov, Jean-Sylvain Camier, Tuo Zhao, Hongyuan Zha, Tzanio Kolev, Robert Anderson, Daniel Faissol

* 14 pages, 13 figures 

  Access Paper or Ask Questions

Learning High Dimensional Wasserstein Geodesics


Feb 22, 2021
Shu Liu, Shaojun Ma, Yongxin Chen, Hongyuan Zha, Haomin Zhou


  Access Paper or Ask Questions

Dealing with Non-Stationarity in Multi-Agent Reinforcement Learning via Trust Region Decomposition


Feb 21, 2021
Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng, Hongyuan Zha

* 32 pages, 23 figures 

  Access Paper or Ask Questions

Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning


Feb 09, 2021
Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng, Yun Hua, Hongyuan Zha

* AAMAS 2021 camera-ready 

  Access Paper or Ask Questions

Hawkes Processes on Graphons


Feb 04, 2021
Hongteng Xu, Dixin Luo, Hongyuan Zha


  Access Paper or Ask Questions

Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances


Dec 19, 2020
Zhang-Hua Fu, Kai-Bin Qiu, Hongyuan Zha

* AAAI2021 

  Access Paper or Ask Questions

Learning Graphons via Structured Gromov-Wasserstein Barycenters


Dec 17, 2020
Hongteng Xu, Dixin Luo, Lawrence Carin, Hongyuan Zha

* AAAI 2021 

  Access Paper or Ask Questions

A Hypergradient Approach to Robust Regression without Correspondence


Nov 30, 2020
Yujia Xie, Yixiu Mao, Simiao Zuo, Hongteng Xu, Xiaojing Ye, Tuo Zhao, Hongyuan Zha


  Access Paper or Ask Questions

Reliable Off-policy Evaluation for Reinforcement Learning


Nov 08, 2020
Jie Wang, Rui Gao, Hongyuan Zha

* 36 pages, 4 figures 

  Access Paper or Ask Questions

Inductive Relational Matrix Completion


Jul 09, 2020
Qitian Wu, Hengrui Zhang, Hongyuan Zha


  Access Paper or Ask Questions

GraphOpt: Learning Optimization Models of Graph Formation


Jul 07, 2020
Rakshit Trivedi, Jiachen Yang, Hongyuan Zha


  Access Paper or Ask Questions

Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification


Jun 29, 2020
Kai Zhang, Yaokang Zhu, Jun Wang, Jie Zhang, Hongyuan Zha


  Access Paper or Ask Questions

Hessian-Free High-Resolution Nesterov Acceleration for Sampling


Jun 22, 2020
Ruilin Li, Hongyuan Zha, Molei Tao


  Access Paper or Ask Questions

Network Diffusions via Neural Mean-Field Dynamics


Jun 16, 2020
Shushan He, Hongyuan Zha, Xiaojing Ye

* Submitted to NIPS2020, 20 pages, 5 figures 

  Access Paper or Ask Questions

Hessian-Free High-Resolution Nesterov Accelerationfor Sampling


Jun 16, 2020
Ruilin Li, Hongyuan Zha, Molei Tao


  Access Paper or Ask Questions

Learning to Incentivize Other Learning Agents


Jun 10, 2020
Jiachen Yang, Ang Li, Mehrdad Farajtabar, Peter Sunehag, Edward Hughes, Hongyuan Zha

* 19 pages, 11 figures 

  Access Paper or Ask Questions

F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning


Apr 17, 2020
Wenhao Li, Bo Jin, Xiangfeng Wang, Junchi Yan, Hongyuan Zha

* arXiv admin note: text overlap with arXiv:1810.02912, arXiv:1803.11485 by other authors 

  Access Paper or Ask Questions

Learning Cost Functions for Optimal Transport


Feb 22, 2020
Haodong Sun, Haomin Zhou, Hongyuan Zha, Xiaojing Ye


  Access Paper or Ask Questions

Transformer Hawkes Process


Feb 21, 2020
Simiao Zuo, Haoming Jiang, Zichong Li, Tuo Zhao, Hongyuan Zha


  Access Paper or Ask Questions

Improving Sampling Accuracy of Stochastic Gradient MCMC Methods via Non-uniform Subsampling of Gradients


Feb 20, 2020
Ruilin Li, Xin Wang, Hongyuan Zha, Molei Tao


  Access Paper or Ask Questions

Differentiable Top-k Operator with Optimal Transport


Feb 18, 2020
Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister


  Access Paper or Ask Questions

Learning Stochastic Behaviour of Aggregate Data


Feb 14, 2020
Shaojun Ma, Shu Liu, Hongyuan Zha, Haomin Zhou


  Access Paper or Ask Questions