Publications

2025

1. ICML

   Sampling from Binary Quadratic Distributions via Stochastic Localization

   Chenguang Wang, Kaiyuan Cui, Weichen Zhao, and 1 more author

   arXiv preprint arXiv:2505.19438, May 2025

   Abs arXiv Bib

   We propose an efficient discrete sampling algorithm based on stochastic localization, achieving consistent performance improvements across multiple standard sampling benchmarks.

   @article{wang2025sampling,
     title = {Sampling from Binary Quadratic Distributions via Stochastic Localization},
     author = {Wang, Chenguang and Cui, Kaiyuan and Zhao, Weichen and Yu, Tianshu},
     journal = {arXiv preprint arXiv:2505.19438},
     year = {2025},
     month = may,
   }

2. KDD

   Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory

   Weichen Zhao, Chenguang Wang, Xinyan Wang, and 3 more authors

   In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1, Jan 2025

   Bib

   @inproceedings{zhao2025understanding,
     title = {Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory},
     author = {Zhao, Weichen and Wang, Chenguang and Wang, Xinyan and Han, Congying and Guo, Tiande and Yu, Tianshu},
     booktitle = {Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1},
     pages = {2043--2054},
     year = {2025},
     month = jan,
   }

3. TMLR

   Efficient Training of Multi-task Neural Solver for Combinatorial Optimization

   Chenguang Wang, Zhang-Hua Fu, Pinyan Lu, and 1 more author

   Transactions on Machine Learning Research, Mar 2025

   Bib

   @article{wang2025efficient,
     title = {Efficient Training of Multi-task Neural Solver for Combinatorial Optimization},
     author = {Wang, Chenguang and Fu, Zhang-Hua and Lu, Pinyan and Yu, Tianshu},
     journal = {Transactions on Machine Learning Research},
     year = {2025},
     month = mar,
   }

4. arXiv

   Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage

   Chenguang Wang, Xiaoyu Zhang, Kaiyuan Cui, and 3 more authors

   arXiv preprint arXiv:2505.19431, Mar 2025

   arXiv Bib

   @article{wang2025importance,
     title = {Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage},
     author = {Wang, Chenguang and Zhang, Xiaoyu and Cui, Kaiyuan and Zhao, Weichen and Guan, Yongtao and Yu, Tianshu},
     journal = {arXiv preprint arXiv:2505.19431},
     year = {2025},
   }

5. arXiv

   Incomplete Data, Complete Dynamics: A Diffusion Approach

   Zihan Zhou, Chenguang Wang, Hongyi Ye, and 2 more authors

   arXiv preprint arXiv:2509.20098, Mar 2025

   arXiv Bib

   @article{zhou2025incomplete,
     title = {Incomplete Data, Complete Dynamics: A Diffusion Approach},
     author = {Zhou, Zihan and Wang, Chenguang and Ye, Hongyi and Guan, Yongtao and Yu, Tianshu},
     journal = {arXiv preprint arXiv:2509.20098},
     year = {2025},
   }

2024

1. TPAMI

   ASP: Learn a Universal Neural Solver!

   Chenguang Wang, Zhouliang Yu, Stephen McAleer, and 2 more authors

   IEEE Transactions on Pattern Analysis and Machine Intelligence, Nov 2024

   Bib HTML

   @article{wang2024asp,
     title = {ASP: Learn a Universal Neural Solver!},
     author = {Wang, Chenguang and Yu, Zhouliang and McAleer, Stephen and Yu, Tianshu and Yang, Yaodong},
     journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
     volume = {46},
     number = {6},
     pages = {4102--4114},
     year = {2024},
     month = nov,
     publisher = {IEEE},
   }

2. arXiv

   Rethinking the "Heatmap+ Monte Carlo Tree Search" Paradigm for Solving Large Scale TSP

   Xuanhao Pan, Chenguang Wang, Chaolong Ying, and 2 more authors

   arXiv preprint arXiv:2411.09238, Nov 2024

   arXiv Bib

   @article{pan2024rethinking,
     title = {Rethinking the "Heatmap+ Monte Carlo Tree Search" Paradigm for Solving Large Scale TSP},
     author = {Pan, Xuanhao and Wang, Chenguang and Ying, Chaolong and Xue, Ye and Yu, Tianshu},
     journal = {arXiv preprint arXiv:2411.09238},
     year = {2024},
   }

3. arXiv

   Towards Principled Task Grouping for Multi-Task Learning

   Chenguang Wang, Xuanhao Pan, and Tianshu Yu

   arXiv preprint arXiv:2402.15328, Nov 2024

   arXiv Bib

   @article{wang2024towards,
     title = {Towards Principled Task Grouping for Multi-Task Learning},
     author = {Wang, Chenguang and Pan, Xuanhao and Yu, Tianshu},
     journal = {arXiv preprint arXiv:2402.15328},
     year = {2024},
   }

2023

1. Appl. Intell.

   Solving uncapacitated P-Median problem with reinforcement learning assisted by graph attention networks

   Chenguang Wang, Congying Han, Tiande Guo, and 1 more author

   Applied Intelligence, Nov 2023

   Bib

   @article{wang2023solving,
     title = {Solving uncapacitated P-Median problem with reinforcement learning assisted by graph attention networks},
     author = {Wang, Chenguang and Han, Congying and Guo, Tiande and Ding, Man},
     journal = {Applied Intelligence},
     volume = {53},
     number = {2},
     pages = {2010--2025},
     year = {2023},
     publisher = {Springer US New York},
   }

2. Neurocomputing

   Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization

   Ziwen Liu, Chenguang Wang, Congying Han, and 1 more author

   Neurocomputing, Nov 2023

   Bib

   @article{liu2023learning,
     title = {Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization},
     author = {Liu, Ziwen and Wang, Chenguang and Han, Congying and Guo, Tiande},
     journal = {Neurocomputing},
     pages = {126392},
     year = {2023},
     publisher = {Elsevier},
   }

3. FAIML

   Exploring over-smoothing in graph attention networks from the Markov chain perspective

   Weichen Zhao, Chenguang Wang, Congying Han, and 1 more author

   In Proceedings of the 2023 International Conference on Frontiers of Artificial Intelligence and Machine Learning, Nov 2023

   Bib

   @inproceedings{zhao2023exploring,
     title = {Exploring over-smoothing in graph attention networks from the Markov chain perspective},
     author = {Zhao, Weichen and Wang, Chenguang and Han, Congying and Guo, Tiande},
     booktitle = {Proceedings of the 2023 International Conference on Frontiers of Artificial Intelligence and Machine Learning},
     pages = {282--288},
     year = {2023},
   }

4. arXiv

   Multireact: Multimodal tools augmented reasoning-acting traces for embodied agent planning

   Zhouliang Yu, Jie Fu, Yao Mu, and 3 more authors

   arXiv preprint, Nov 2023

   Bib

   @article{yu2023multireact,
     title = {Multireact: Multimodal tools augmented reasoning-acting traces for embodied agent planning},
     author = {Yu, Zhouliang and Fu, Jie and Mu, Yao and Wang, Chenguang and Shao, Lin and Yang, Yaodong},
     journal = {arXiv preprint},
     year = {2023},
   }

2022

1. CoRR

   Analysis of Graph Neural Networks with Theory of Markov Chains

   Weichen Zhao, Chenguang Wang, Congying Han, and 1 more author

   CoRR, Nov 2022

   Bib

   @article{zhao2022analysis,
     title = {Analysis of Graph Neural Networks with Theory of Markov Chains},
     author = {Zhao, Weichen and Wang, Chenguang and Han, Congying and Guo, Tiande},
     journal = {CoRR},
     year = {2022},
   }

2021

1. ICLR Workshop

   A game-theoretic approach for improving generalization ability of TSP solvers

   Chenguang Wang, Yaodong Yang, Oliver Slumbers, and 4 more authors

   In ICLR 2022 Workshop: Gamification and Multiagent Solutions (Spotlight), Nov 2021

   arXiv Bib

   @inproceedings{wang2021game,
     title = {A game-theoretic approach for improving generalization ability of TSP solvers},
     author = {Wang, Chenguang and Yang, Yaodong and Slumbers, Oliver and Han, Congying and Guo, Tiande and Zhang, Haifeng and Wang, Jun},
     booktitle = {ICLR 2022 Workshop: Gamification and Multiagent Solutions (Spotlight)},
     year = {2021},
   }