Xi Sheryl Zhang, Associate Professor    

Institute of Automation, Chinese Academy of Sciences

Email: xi.zhang@ia.ac.cn

Office: 95 Zhongguancun East Road, Room 1119, Beijing, China, 100190

Research Areas

Reinforcement Learning, Machine Learning, Computer Vision

Experience

Xi Sheryl Zhang is an Associate Professor at the Institute of Automation, Chinese Academy of Sciences. She obtained her Ph.D. in Pattern Recognition and Intelligent Systems from the University of Chinese Academy of Sciences in July 2015. Before joining Cornell University as a Postdoc in 2017,  Xi was a Research Scientist at Huawei Noah's Ark Lab. In 2020, she joined the Institute of Automation, Chinese Academy of Sciences, as an Associate Professor. Her research mainly focuses on machine learning, computer vision, and reinforcement learning.
Xi has published nearly forty papers in international conferences such as ICLR, ICML, CVPR, AAAI, and KDD. She has led his team to win the NeurIPS competition and the Annual Outstanding Paper Award from the American Medical Informatics Association. Her work applying deep learning to brain neuroscience has received the Blue Ribbon Award from the International Parkinson and Movement Disorder Society and the Boehringer Ingelheim Fellowship.
Xi has served as a program committee member or reviewer for international journals, including TKDE, TNNLS, etc., and conferences, including NeurIPS, ICML, ICLR, SIGKDD, AAAI, etc. She has also chaired the program committee of the SIAM SDM workshop. Xi has been the Principal Investigator for projects under the Major Program of Brain Science and Brain-Like Research of China's National Key R&D Program. She has also received research funding from the CCF-Tencent Rhino Bird Fund. She has been a core researcher in projects such as the National Key R&D Program for the Next Generation Artificial Intelligence and the Natural Science Foundation of China.


Publications

   
Papers

  • Intrinsic Action Tendency Consistency for Cooperative Multi-Agent Reinforcement Learning, Proceedings of the AAAI Conference on Artificial Intelligence, 2024
  • GraphLeak: Patient record leakage through gradients with knowledge graph, The Web Conference, 2024
  • A New Pre-Training Paradigm for Offline Multi-Agent Reinforcement Learning with Suboptimal Data, ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing, 2024
  • On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning, The Eleventh International Conference on Learning Representations, 2023
  • Multi-Granularity Pruning for Model Acceleration on Mobile Devices, European Conference on Computer Vision, 2022
  • Differentially Private Federated Learning with Local Regularization and Sparsification, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
  • APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
  • DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy, AAAI, 2022
  • MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Records, Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 2019
  • Integrative Analysis of Patient Health Records and Neuroimages via Memory-based Graph Convolutional Network, IEEE International Conference on Data Mining, 2018
  • Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson's Disease., AMIA Annual Symposium Proceedings, 2018
  • Patient Subtyping via Time-aware LSTM Networks, Proceedings of the 23th ACM SIGKDD international conference on knowledge discovery & data mining, 2017


Patents

  • Community Question Answering-Based Article Recommendation Method, System, and User Device, 2019, US20190303768A1