Runzhong Wang - 汪润中
runzhong DOT wang AT sjtu DOT edu DOT cn

I am a final year PhD student at AI Institute and Department of CSE, Shanghai Jiao Tong University (SJTU), supervised by Prof. Xiaokang Yang and Prof. Junchi Yan.
I am interested in Machine Learning, Graph Learning and related Optimization Problems. I am also interested in tackling real-world social issues via my technical expertise.
I serve as the reviewer for conferences (NeurIPS 2020/2021/2022, ICML 2022, ICLR 2022/2023, CVPR 2020/2021/2022, ICCV 2021, ECCV 2022, AAAI 2021/2022, CIKM 2019, MM 2021/2022) and journals (IJCV, TPAMI, PR, TMM, TCSVT). I serve as the class monitor of Wen-Tsun Wu Honorary Doctoral Class at Shanghai Jiao Tong University since 2019.

What's New

  • Pygmtools now supports numpy/pytorch/jittor/paddle. Install it by pip install pygmtools!
  • One paper on the federated learning is accepted by ICML2022! Congrats to Chang Liu and Chenfei!
  • One paper on the robustness of visual graph matching is accepted by CVPR2022! Congrats to Qibing and Qingquan!
  • One paper on learning combinatorial optimization is accepted by NeurIPS 2021!

Code and Software

⭐Thank you for staring my code!⭐ It encourages me to work harder on more open-source projects!

pygmtools

  • A graph matching tool with python API.
  • GPU compatible and deep learning ready.
  • Supported backends: numpy, pytorch, jittor, and paddle.
  • Install it by pip install pygmtools.

ThinkMatch

  • A collection of state-of-the-art deep graph matching models.
  • Official implementation of our models: NGM(v2), GANN-MGM, PCA-GM, CIE.
  • Implementation of other state-of-the-art models: GMN, BBGM.

Awesome ML4CO

  • A collection of awesome machine learning for combinatorial optimization papers.
  • Pull Requests are welcomed to add more papers!

PPO-BiHyb

  • A bi-level framework for learning combinatorial optimization.
  • Upper-level: A reinforcement learning model (PPO) to optmize the graph structure.
  • Lower-level: A fast heuristic algorithm running on the optimized graph.
  • Official implementation on 3 problems: DAG scheduling, graph edit distance and Hamiltonian cycle problem.

Publications

Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning.
Chang Liu, Chenfei Lou, Runzhong Wang, Alan Yuhan Xi, Li Shen, Junchi Yan.
ICML 2022.
[paper] [code]

Appearance and structure aware robust deep visual graph matching: Attack, defense and beyond.
Qibing Ren, Qingquan Bao, Runzhong Wang, Junchi Yan.
CVPR 2022.
[paper] [code]

A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs.
Runzhong Wang, Zhigang Hua, Gan Liu, Jiayi Zhang, Junchi Yan, Feng Qi, Shuang Yang, Jun Zhou, Xiaokang Yang.
NeurIPS 2021.
[paper] [code]

Deep Latent Graph Matching.
Tianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li.
ICML 2021.
[paper]

Deep Reinforcement Learning of Graph Matching.
Chang Liu, Runzhong Wang, Zetian Jiang, Junchi Yan.
Preprint, under review.
[preprint]

Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching.
Runzhong Wang, Junchi Yan, Xiaokang Yang.
TPAMI 2022 (vol. 44, no. 9, pp. 5261-5279).
Best poster award at Internation Conference on Data Science 2019.
[paper] [project page] [code]

Combinatorial Learning of Graph Edit Distance via Dynamic Embedding.
Runzhong Wang, Tianqi Zhang, Tianshu Yu, Junchi Yan, Xiaokang Yang.
CVPR 2021.
[paper] [code]

Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning.
Runzhong Wang, Junchi Yan, Xiaokang Yang.
NeurIPS 2020.
[paper] [project page] [code]

Combinatorial Learning of Robust Deep Graph Matching: an Embedding based Approach.
Runzhong Wang, Junchi Yan, Xiaokang Yang.
TPAMI.
[paper] [project page] [code]

Learning deep graph matching with channel-independent embedding and Hungarian attention.
Tianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li.
ICLR 2020.
[paper] [code]

Learning Combinatorial Embedding Networks for Deep Graph Matching.
Runzhong Wang, Junchi Yan, Xiaokang Yang.
ICCV 2019 (oral).
[paper] [project page] [code] [slides]

InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting.
*Runzhong Wang, *Hao-shu Fang, *Jianhua Sun, Minghao Gou, Yong-Lu Li, Cewu Lu. (* equal contribution)
ICCV 2019.
[paper] [code]

Education

From Sep 2019
PhD of Comupter Science and Technology
Wen-Tsün Wu Honorable Class, AI Institute of Shanghai Jiao Tong University
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University (SJTU)

Sep 2015 to Jun 2019
Bachelor of Engineering in Information Engineering
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University (SJTU)

Awards

National Scholarship in 2022 (国家奖学金)

Outstanding Reviewer of ICML 2022

CCF-CV Outstanding Young Researcher Award in 2021 (3 winners in China, CCF-CV学术新锐奖)

Computer Science Fellowship at Shanghai Jiao Tong University in 2021 (3 winners SJTU, 上海交大85届计算机系奖学金)

Nomination Award of the 2021 MSRA Fellowship (17 nominations in Asia)

Jiachi Yang honorary scholarship in 2020 (杨嘉墀奖学金)

Best poster award at International Conference on Data Science 2019 (1 winner)

Xu Zhang honorary scholarship in 2019 (张煦奖学金)