I’m Zhongkai Hao, a second-year Ph.D. student of TSAIL Group at Tsinghua University, supervised by Prof. Jun Zhu, Prof. Hang Su. and Prof. Jian Song. My research interests are mainly about AI for science. I’m also interested in generative models and reinforcement learning.

Before that, I obtained my Bachelor of Science degree from School of Gifted Young of USTC in July, 2021, majored in Computational Mathematics.

Email: hzj21@mails.tsinghua.edu.cn; hzk011003@gmail.com; hzk171805@mail.ustc.edu.cn

News

• We have established a large scale benchmark on PINNs, PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
  It provides 10+ PINN variants evaluated on 22 challenging PDEs, which is the largest benchmark for PINNs. [code]
  
• We have a survey paper about physics-informed machine learning available on arXiv: Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications
  It provides insights about how to integrate physical prior into machine learning. It also exhaustively introduces recent progress of Physics-informed Neural Networks and Neural Operators.
  
• We have a automatically renewing paper list about AI for Science: Machine Learning for Science and Engineering PaperList
  Although this paperlist might be inaccurate now, it is a good tool to track new papers about AI4Science. We will improve its filtration efficiency further.

Selected Publications

• PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
  Zhongkai Hao, Jiachen Yao, Chang Su, Hang Su, Ziao Wang, Fanzhi Lu, Zeyu Xia, Yichi Zhang, Songming Liu, Lu Lu, Jun Zhu
  [arXiv] [code]
  
• DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
  Zhongkai Hao, Chang Su, Songming Liu, Julius Berner, Chengyang Ying, Hang Su, Anima Anandkumar, Jian Song, Jun Zhu
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024
  [arXiv] [code]
  
• Improved Operator Learning by Orthogonal Attention
  Zipeng Xiao, Zhongkai Hao, Bokai Lin, Zhijie Deng, Hang Su
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024 (Spotlight)
  [arXiv] [code]
  
• Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations
  Ze Cheng, Zhongkai Hao, Xiaoqiang Wang, Jianing Huang, Youjia Wu, Xudan Liu, Yiru Zhao, Songming Liu, Hang Su
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024
  
• PAPM: A Physics-aware Proxy Model for Process Systems
  Pengwei Liu, Zhongkai Hao, Xingyu Ren, Hangjie Yuan, Jiayang Ren, Dong Ni
  International Conference on Machine Learning (ICML), Vienna, Austria, 2024
  [arXiv] [code]
  
• Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
  Hong Wang *, Zhongkai Hao *, Jie Wang, Zijie Geng, Zhen Wang, Bin Li, Feng Wu
  The Twelfth International Conference on Learning Representations (ICLR), Vienna, Austria, 2024 (Spotlight)
  [arXiv] [code]
  
• Full-atom protein pocket design via iterative refinement
  Zaixi Zhang, Zepu Lu, Zhongkai Hao, Marinka Zitnik, Qi Liu
  Advances in Neural Information Processing Systems(NeurIPS), New Orleans, USA, 2023 (Spotlight)
  [arXiv] [code]
  
• GNOT: A General Neural Operator Transformer for Operator Learning
  Zhongkai Hao, Chengyang Ying, Zhengyi Wang, Hang Su, Yinpeng Dong, Songming Liu, Ze Cheng, Jun Zhu, Jian Song
  International Conference on Machine Learning (ICML), Hawaii, USA, 2023
  [arXiv] [code]
  
• NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data
  Songming Liu, Zhongkai Hao, Chengyang Ying, Hang Su, Ze Cheng, Jun Zhu
  International Conference on Machine Learning (ICML), Hawaii, USA, 2023
  [arxiv] [code]
  
• MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural Networks
  Jiachen Yao, Chang Su, Zhongkai Hao, Songming Liu, Hang Su, Jun Zhu
  International Conference on Machine Learning (ICML), Hawaii, USA, 2023
  [arxiv] [[code]]
  
• Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications
  Zhongkai Hao, Songming Liu, Yichi Zhang, Chengyang Ying, Yao Feng, Hang Su, Jun Zhu, [arXiv]
  
• Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden’s Hypergradients
  Zhongkai Hao, Chengyang Ying, Hang Su, Jun Zhu, Jian Song, Ze Cheng
  International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023 [pdf] [arXiv] [code]
  
• Equivariant Energy-Guided SDE for Inverse Molecular Design
  Fan Bao, Min Zhao, Zhongkai Hao, Peiyao Li, Chongxuan Li, Jun Zhu
  International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023 [pdf] [arXiv] [code]
  
• A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs
  Songming Liu, Zhongkai Hao, Chengyang Ying, Hang Su, Jun Zhu, Ze Cheng
  Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2022. [pdf] [arXiv] [code]
  
• GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing
  Zhongkai Hao, Chengyang Ying, Yinpeng Dong, Hang Su, Jian Song, Jun Zhu
  International Conference on Machine Learning (ICML), Baltimore, USA, 2022. [pdf] [arXiv]
  
• CLUSTER ATTACK: Query-based Adversarial Attacks on Graphs with Graph-Dependent Priors
  Zhengyi Wang, Zhongkai Hao, Ziqiao Wang, Hang Su, Jun Zhu
  International Joint Conference on Artificial Intelligence (IJCAI), 2022. (Long Oral, Accept rate~3.8%) [pdf] [Code]
  
• ASGN: An active semi-supervised graph neural network for molecular property prediction
  Zhongkai Hao, Chengqiang Lu, Zheyuan Hu, Hao Wang, Zhenya Huang, Qi Liu, Enhong Chen, Cheekong Lee
  Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (SIGKDD), 2020,
  [pdf], [code]
  

Projects

• We (Zhongkai Hao, Chengyang Ying, Zhengyi Wang) automatically crawl and classify articles about NN4Phys.
  [link] –>

Services

Reviewer for IJCAI 2023, ICML 2023, NeurIPS 2023

Reviewer for IJCAI 2022, ICML 2022, NeurIPS 2022

Reviewer for KDD 2021, PRCV 2021

Teaching

• 2023 Spring, TA in Statistical Machine Learning, instructed by Prof. Hang Su
• 2022 Spring, TA in Statistical Machine Learning, instructed by Prof. Hang Su

Talks & Slides

Reading group slides:

• Applications of Machine Learning in Science and Engineering
• Tensor Decomposition Methods and Applications

Invited talks:

• Slides about Physics-informed Machine Learning at Lu’s group.

Curriculum Vitae

My curriculum vitae is here.

Last update: Nov 1st by Zhongkai Hao