wanyu.jpg

Department of Computing

The Hong Kong Polytechnic University

PQ730, Mong Man Wai Building

Hung Hom, Kowloon, Hong Kong

Wanyu is an Assistant Professor in the Department of Computing at The Hong Kong Polytechnic University. Wanyu is serving as an Associate Editor for  IEEE Transactions On Neural Networks and Learning Systems (TNNLS).

Wanyu’s main research interest is in the broad area of creating AI with safe and ethical objectives. Specifically, we focus on interpretability, fairness, robustness, and privacy-preservation of various kinds of machine learning models, including graph learning models and large pre-trained language models.


Research Team

  • Jian Chen (Post-Doctoral Fellow, Previously Ph.D. at HUST)
  • Zhenzhong Wang (Ph.D. Candidate, Previously Master Student at Xiamen University)
  • Yee Chung Cheung (Doctor of FinTech Candidate)
  • Mingxuan Ouyang (Research Assistant and Incoming Ph.D. Candidate, Previously Master Student at HK PolyU)
  • Xindi Zheng (Incoming Ph.D. Candidate, Previously Master Student at University of Southern California)
  • Zhuoran Li (Research Assistant, Previously Undergraduate at University of Washington-Seattle)
  • Zehui Lin (Research Assistant, Previously Undergraduate Student at University of Sydney)
  • Ziyi Zhang (Research Assistant, Master Student at South China University of Technology)

    • We are looking for motivated Post-Doctoral Fellows and Ph.D. Students who are interested and experienced in trustworthy AI and generative AI. Send me your CV (GPA, publications, etc.) and your transcript via email if you are interested in working with me at PolyU. Candidates who have strong mathematics backgrounds and programming skills are preferred.

news

Dec 10, 2023 Our two papers, Generating Diagnostic and Actionable Explanations for Fair Graph Neural Networks and Self-Prompt Dehazing Transformers with Depth-Consistency, were accepted by AAAI 2024. :smile:
Nov 24, 2023 Our paper, Predicting Dynamic Responses of Continuous Deformable Bodies: A Graph-Based Learning Approach, was accepted by Computer Methods in Applied Mechanics and Engineering. :sparkles:
Jul 27, 2023 Invited talk titled “Towards Generative Causal Explanations for Graph Neural Networks” at the International Scholars Forum, hosted by Zhejiang University.
Jul 15, 2023 Serving as a Session Chair for  43rd IEEE International Conference on Distributed Computing Systems (ICDCS).
Feb 23, 2023 Our paper, On Practical Differentially Private and Byzantine-Resilient Federated Learning, was accepted by SIGMOD 2023. :sparkles:
Dec 12, 2022 Our paper, Robust Graph Meta-Learning via Manifold Calibration with Proxy Subgraphs, was accepted by AAAI 2023. :sparkles:
Sep 21, 2022 Our paper, Rigging GNN-Based Social Status by Adversarial Attacks in Signed Social Networks, was accepted by TIFS 2022. :smile:
Sep 11, 2022 Our paper on GNN privacy, Solitude, was accepted by TIFS 2022. :smile: