Zaixi Zhang PhD candidate Department of Computer Science and Engineering University of Science and Technology of China 100 Fuxing Rd, Information Intelligence Building 709 Anhui Province, Hefei City China Email: zaixi@mail.ustc.edu.cn	My Photo

Biography

I'm a PhD student in BASE Group, Department of Computer Science, University of Science and Technology of China (USTC). My advisors is Prof. Qi Liu. In 2019, I got bachelor degree from School of the Gifted Young, USTC, majoring in Theoretical and Applied Mechanics. In 2021, I was a research intern in Tencent company, mentored by Dr. Chee-Kong Lee. I've had fortune of collaborating with Prof. Neil Gong, Prof. Earl Dowell and Prof. Marinka Zitnik.

I have broad research interests in AI for Science and Trustworthy AI. Recently I am focusing on the intersection of AI and drug discovery.

I am now a visiting PhD student with Prof. Marinka Zitnik at Harvard University.

Representative Publications (Google Scholar, Code)

AI for Science:
• Full Atom Protein Pocket Design via Iterative Refinement, [Code]
  Zaixi Zhang, Zepu Lu, Zhongkai Hao, Marinka Zitnik, Qi Liu
  The 37th Advances in Neural Information Processing Systems (NeurIPS (Spotlight)), 2023.
  

• A Systematic Survey in Geometric Deep Learning for Structure-based Drug Design, [Awesome-SBDD]
  Zaixi Zhang, Jiaxian Yan, Qi Liu, Enhong Chen, Marinka Zitnik
  on submission, 2023.

• An Equivariant Generative Framework for Molecular Graph-Structure Co-Design, [Code]
  Zaixi Zhang, Qi Liu, Chee-Kong Lee, Chang-Yu Hsieh, Enhong Chen
  Chemical Science, 2023.

• Learning Subpocket Prototypes For Generalizable Structure Based Drug Design,
  Zaixi Zhang, Qi Liu
  The Fortieth International Conference on Machine Learning (ICML), 2023.
  

• Molecule Generation For Target Protein Binding with Structural Motifs, [Code]
  Zaixi Zhang, Yaosen Min, Shuxin Zheng, Qi Liu
  The Eleventh International Conference on Learning Representations (ICLR), 2023.
  

• Hierachical Graph Transformer with Adaptive Node Sampling, [Code]
  Zaixi Zhang, Qi Liu, Qingyong Hu, Chee-Kong Lee
  The 36th Advances in Neural Information Processing Systems (NeurIPS (Spotlight)), 2022.
  

• Graph Self-Supervised Learning for Optoelectronic Properties of Organic Semiconductors, [Code]
  Zaixi Zhang, Qi Liu, Shengyu Zhang, Chang-Yu Hsieh, Liang Shi, Chee-Kong Lee.
  Thirty-ninth International Conference on Machine Learning AI4Science Workshop, (ICML Workshop) 2022.
  

• Motif-based Graph Self-Supervised Learning for Molecular Property Prediction, [Code]
  Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu, Chee-Kong Lee
  The 35th Advances in Neural Information Processing Systems (NeurIPS), 2021.
  

Trustworthy AI:
• Backdoor Defense via Deconfounded Representation Learning, [Code]
  Zaixi Zhang, Qi Liu, Zhicai Wang, Zepu Lu, Qingyong Hu
  The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
  

• FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information,
  Xiaoyu Cao, Jinyuan Jia, Zaixi Zhang, Neil Gong
  The 44th IEEE Symposium on Security and Privacy (IEEE S&P), 2023.
  

• FLCert: Provably Secure Federated Learning against Poisoning Attacks via Ensemble Methods,
  Xiaoyu Cao, Zaixi Zhang, Jinyuan Jia, Neil Gong
  IEEE Transactions on Information Forensics and Security (TIFS), 2022.

• Model Inversion Attacks Against Graph Neural Networks, [Code]
  Zaixi Zhang, Qi Liu, Zhenya Huang, Hao Wang, Chee-Kong Lee, Enhong Chen.
  Transactions on Knowledge and Data Engineering (TKDE), 2022.

• FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients, [Code]
  Zaixi Zhang, Xiaoyu Cao, Jinyuan Jia, Neil Gong
  The 28th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD), 2022.
  

• ProtGNN: Towards Self-Explaining Graph Neural Networks, [Code]
  Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu, Chee-Kong Lee
  The 36th AAAI Conference on Artificial Intelligence (AAAI), 2022.
  

• GraphMI: Extracting Private Graph Data from Graph Neural Networks, [Code]
  Zaixi Zhang, Qi Liu, Zhenya Huang, Hao Wang, Chengqiang Lu, Chuanren Liu, Enhong Chen
  The 30th International Joint Conference on Artificial Intelligence (IJCAI), 2021.
  

• Backdoor attacks to graph neural networks, [Code]
  Zaixi Zhang, Jinyuan Jia, Binghui Wang, Neil Gong
  The 26th ACM Symposium on Access Control Models and Technologies (SACMAT), 2021.
  

Academic Services

Reviewer: AAAI, NeurIPS, CVPR, ICCV, KDD, AISTATS, TKDE, TPAMI, TIFS.

Talks

• ProtGNN: Towards Self-Explaining Graph Neural Networks. Recording, AI Time, May. 24, 2022

• FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients. Recording, AI Time, July. 6, 2022

Honors & Awards

Best Presentation Award of 2021 Tencent Rhino-Bird Research Elite Program

Third Prize Scholarship of 2021 Tencent Rhino-Bird Research Elite Program (Top 6 of 62)

National Scholarship, 2021.

Tencent Excellent Intern (Top 5% Interns), 2021.

Tencent Rhino Bird Talents Program, 2021.

Graduate Scholarship, Department of Computer Science and Engineering, University of Science and Technology of China, 2020.

Honorary graduate student of USTC (Top 5%), University of Science and Technology of China, 2019.

Excellent Student Scholarship, University of Science and Technology of China, 2016-2019.

Miscellany

Hobbies: Soccer, Swimming, PC Games, Hiking.

Last Updated by Zaixi: July 2 2023