张希,中国科学院自动化研究所副研究员。于2015年7月获得中国科学院大学博士学位,专业为模式识别与智能系统。后担任华为诺亚方舟实验室研究科学家,2017年加入康奈尔大学担任博士后研究员,2020年加入中科院自动化所。主要从事机器学习、计算机视觉、强化学习等方面的研究。在ICLR、ICML、CVPR、AAAI、KDD等顶级国际会议上发表论文近四十篇。带领团队获得NeurIPS竞赛冠军、美国医学信息学会年度优秀论文奖,深度学习应用于脑神经科学的工作获得国际运动障碍协会蓝丝带奖,Boehringer Ingelheim Fellowship获得者。长期担任IEEE TKDE、IEEE TNNLS等国际期刊和NeurIPS、ICML、ICLR、SIGKDD、AAAI等国际会议程序委员会成员或审稿人,曾担任SIAM SDM workshop程序委员会主席。主持科技创新2030脑科学与类脑研究重大项目子课题、CCF-腾讯犀牛鸟基金,作为核心研究者参与科技创新2030新一代人工智能、国家自然科学基金等多项科研项目。
机器学习、计算机视觉、强化学习
面向多模态协同类脑听觉模型计算的软硬件协同计算系统,科技部“新一代人工智能”重大项目,子课题负责人,2021.12—2026.11
医学多模态技术研究,CCF-Tencent犀牛鸟开放基金,2022.10—2023.10
[1] Xi Sheryl Zhang, Andy Tang, Hiroko H Dodge, Jiayu Zhou, Fei Wang. Metapred: Meta-learning for clinical risk prediction with limited patient electronic health records. ACM SIGKDD 2019 (CCF-A) (AMIA Highlighted Paper Award).
[2] Inci M Baytas, Cao Xiao, Xi Sheryl Zhang, Fei Wang, Anil K Jain, Jiayu Zhou. Patient subtyping via time-aware LSTM networks. ACM SIGKDD 2017 (CCF-A).
[3] Xi Sheryl Zhang, Jingyuan Chou, Fei Wang. Integrative analysis of patient health records and neuroimages via memory-based graph convolutional network. IEEE International Conference on Data Mining 2018. (Acceptance rate 8.86%)
[4] Xi Sheryl Zhang, Lifang He, Kun Chen, Yuan Luo, Jiayu Zhou, Fei Wang. Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson's Disease. AMIA Annual Symposium Proceedings 2018.
[5] Xi Sheryl Zhang, Jingyuan Chou, Jian Liang, Cao Xiao, Yize Zhao, Harini Sarva, Claire Henchcliffe, Fei Wang. Data-driven subtyping of Parkinson’s disease using longitudinal clinical records: a cohort study. Nature Scientific Reports 2019. (Blue Ribbon Highlights, Top 100 in Neuroscience).
[6] Xi Zhang, Dandi Chen, Yongjun Zhu, Chao Che, Chang Su, Stan Zhao, Xu Min, Fei Wang. Multi-view ensemble classification for clinically actionable genetic mutations. NeurIPS 2017 (1st Prize, Top 1 out of 1386 teams).
[7] Sicong Liu, Xi Sheryl Zhang*, Yushuo Li, Yifan Zhang, Jian Cheng. On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning. ICLR 2023. (学生一作,通讯作者)
[8] Jiahao Lu, Xi Sheryl Zhang, Tianli Zhao, Xiangyu He, Jian Cheng. APRIL: Finding the Achilles' heel on privacy for vision transformers. CVPR 2022 (CCF-A). (学生一作)
[9] Anda Cheng, Peisong Wang, Xi Sheryl Zhang, Jian Cheng. Differentially private federated learning with local regularization and sparsification. CVPR 2022 (CCF-A). (学生一作,联合指导)
[10] Anda Cheng, Jiaxing Wang, Xi Sheryl Zhang, Qiang Chen, Peisong Wang, Jian Cheng. DPNAS: Neural architecture search for deep learning with differential privacy. AAAI 2022 (CCF-A).
[1] Boehringer Ingelheim Fellowship, 康奈尔大学和Boehringer Ingelheim制药联合授予博士后会士
[2] NeurIPS Challenge:Classifying Clinically Actionable Genetic Mutations, 1386队排名第1 (第一作者)
[3] Blue Ribbon Highlights Paper Award, 国际运动障碍协会(MDS)授予(第一作者)
[4] AMIA Highlights Paper Award,美国医学信息学会授予(第一作者)