头像

张凯

教授教授

计算机科学与技术学院      

导航

  • 个人资料
  • 研究方向
  • 招生与培养
  • 开授课程
  • 科研项目
  • 学术成果
  • 荣誉及奖励

个人资料

  • 部门： 计算机科学与技术学院
  • 毕业院校： 香港科技大学
  • 学位： 博士
  • 学历： 博士
  • 邮编：
  • 联系电话：
  • 传真：
  • 电子邮箱： kzhang@cs.ecnu.edu.cn
  • 办公地址： 理科大楼804
  • 通讯地址：

教育经历

2004-2008 香港科技大学计算机系 博士

2001-2004 中科院自动化所 硕士

工作经历

  • 2021 - 至今  华东师范大学计算机科学与技术学院 教授

  • 2017 - 2021  Temple University 计算机信息科学系 副教授

  • 2013 - 2017  NEC Labs America 研究员

  • 2011 - 2013  Siemens Corporate Research 研究员

  • 2008 - 2010  Lawrence Berkeley National Lab 博士后

个人简介

博士，博士生导师。博士毕业于香港科技大学计算机工程系，先后在美国劳伦斯伯克利国家实验室、西门子研究院，NEC实验室（普林斯顿）工作。在加入华东师范大学前曾任美国Temple University（天普大学）计算机科学及工程系副教授。主要从事机器学习、图神经网络、脑科学、生物信息和推荐系统研究。在机器学习权威期刊和顶级会议发表论文80余篇，其中包括CCF A类论文40余篇。获得2016年ACM SIGKDD 数据挖掘会议最佳论文提名奖，及NEC Labs商业贡献奖。在动态脑功能网络方面的研究工作以封面文章发表在著名脑科学杂志Brain（2016年8月），并获得美国麦克阿瑟奖得主、宾夕法尼亚大学Danielee Bassett撰写名为“灵活的大脑”的评论文章，认为“该工作是我们理解动态功能网络的基石”。国际专利授权7项。


欢迎对人工智能，语言/生成模型，AI for Science感兴趣的同学加入我的研究团队！

社会兼职

研究方向

  • 语言模型，Transformer（注意力机制、位置编码、记忆网络、检索模型）

  • 蛋白质语言模型、构象预测、动力学模拟、生成模型

  • 图神经网络、表征学习、推荐系统

  • 时间序列分析预测、异常检测、动态网络分析

  • fMRI数据分析、脑网络、精神疾病诊断

招生与培养

开授课程

2022 秋季 线性代数


2020 Spring Advanced Topics in Large-Scale Machine Learning


2019 Spring Deep Neural Networks 


2018 Autumn Fundations of Machine Learning 


科研项目

2023-2027 “蛋白质动力学分析及预测 AI 算法发展”国家重点研发计划（人工智能预测蛋白质动力学新技术开发及其在新药研发中的应用-课题1主持）


2023-2027 “复杂系统启发的新型图神经网络信息处理机制研究” 国家自然科学面上基金 （主持）


2022-2026 “中国学龄儿童脑智力发育队列研究-华东师范大学队列建设” （科技创新2030 --“脑科学与类脑研究”重大项目课题，参与）


2021-2023 “动态子网络时空演化深度建模及其脑科学应用研究”浦江人才计划（主持）

学术成果

  1. Yu Dai, Junchen Shen, Zijie Zhai, Danlin Liu, Jinyang Chen, Yu Sun, Ping Li, Jie Zhang, Kai Zhang. High-Order Contrastive Learning  with Fine-grained Comparative Levels for Sparse Ordinal Tensor Completion. Proceedings of the 41st International Conference on Machine Learning, ICML 2024. 

  2. Kai Zhang, Junchen Shen, Gaoqi He, Yu Sun, Hongyuan Zha, Haibin Ling, Hongli li, Jie Zhang. A Transformative Topological Representation for Link Modelling, Prediction and Cross-Domain Network Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, TPAMI 2024.

  3. Pan Li, Ping Li, Kai Zhang. Dual-Channel Span for Aspect Sentiment Triplet Extraction. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023.

  4. Juyong Jiang, Bingqing Wu, Ling Chen, Kai Zhang, Sunghun Kim, Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting, CIKM 2023.

  5. Juyong Jiang, Peiyan Zhang, Yingtao Luo, Chaozhuo Li, Kai Zhang, Senzhang Wang, Xing Xie, Sunghun Kim and Jaeboum KimAdaMCT: Adaptive Mixture of CNN-Transformer for Sequential Recommendation, CIKM 2023。

  6. Yue Qu,  Chuanren Liu,  Kai Zhang,  Keli Xiao,  Bo Jin,  Hui Xiong, Diagnostic Sparse Connectivity Networks With Regularization Template, IEEE Transactions on Knowledge and Data Engineering 2023, Jan. vol. 35, pp. 307-320.

  7. Xinran Wu, Lena Palaniyappan, Gechang Yu, Kai Zhang, Jakob Seidlitz, Zhaowen Liu, Xiangzhen Kong, Gunter Schumann, Jianfeng Feng, Barbara J. Sahakian, Trevor W. Robbins, Edward Bullmore & Jie Zhang. Morphometric dis-similarity between cortical and subcortical areas underlies cognitive function and psychiatric symptomatology: a preadolescence study from ABCD. Nature Molecular Psychiatry 2022.

  8. Jie Wang, Zihao Shen, Yichen Liao, Zhen Yuan, Shiliang Li, Gaoqi He, Man Lan, Xuhong Qian, Kai Zhang, Honglin Li. Multi-modal chemical information reconstruction from images and texts for exploring the near-drug space. Brief in Bioinformatics,23(6):2022

  9. Xinran Wu, Xiangzhen Kong, Deniz Vatansever, Zhaowen Liu, Kai Zhang, Barbara J. Sahakian, Trevor W. Robbins, Jianfeng Feng, Paul Thompson, Jie Zhang. Dynamic changes in brain lateralization correlate with human cognitive performance, PLOS Biology, March 17,2022.

  10. Yaokang Zhu, Kai Zhang, Jun Wang, Jie Zhang, Hongyuan Zha, Haibin Ling, Structural Landmarking and Interaction Modelling: A “SLIM” Network for Graph ClassificationProceedings of the AAAI Conference on Artificial Intelligence AAAI 2022.

  11. Zhu, Yaokang, Jun Wang, Jie Zhang, Kai Zhang. Node Embedding and Classification with Adaptive Structural Fingerprint. Neurocomputing 502: 196-208 (2022).

  12. Tianyi Gu; Kaiwen Huang; Jie Zhang; Kai Zhang; Ping Li; Fast Convolutional Factorization Machine with Enhanced Robustness, IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021

  13. GMOT-40: A Benchmark for Generic Multiple Object Tracking.Hexin Bai, Wensheng Cheng, Peng Chu, Juehuan Liu, Kai Zhang, Haibin Ling; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 6719-6728.

  14. Conor Tillinghast, Shikai Fang, Kai Zhang, and Shandian Zhe. Probabilistic Neural-Kernel Tensor Decom-position. International Conference on Data Mining (ICDM 2020).

  15. Shikai Fang, Shandian Zhe, Kuang-chih Lee, Online Bayesian Sparse Learning with Spike and Slab Pri-ors”. International Conference on Data Mining.Juyong Jiang, Jie Zhang, Kai Zhang (ICDM 2020).

  16. Cascaded Semantic and Positional Self-Attention Network for Doc-ument Classification. Findings of the Association for Computational Linguistics: EMNLP 2020.

  17. Kai Zhang, Yaokang Zhu, Jie Zhang, Jun Wang.  Adaptive Structural Fingerprints for Graph AttentionNetworks.8th International Conference on Learning Representations (ICLR 2020).

  18. Kai Zhang, Jun Liu, Jie Zhang, Jun Wang. Greedy Orthogonal Pivoting for Non-negative Matrix Factor-ization.36th International Conference on Machine Learning (ICML 2019).

  19. Yanjun  Li,Kai  Zhang,  Jun  Wang,  Sanjiv  Kumar.   Learning  Adaptive  Random  Features.33th  AAAIConference on Artificial Intelligence (AAAI 2019).

  20. Wenchao  Yu,  Wei  Cheng,  Charu  C.  Aggarwal,Kai  Zhang,  Haifeng  Chen,  and  Wei  Wang.  NetWalk:A Flexible Deep Embedding Approach for Anomaly Detection in Dynamic Networks.ACM SIGKDDInternational Conference on Knowledge Discovery and Data Mining (KDD 2018).

  21. Hancheng Ge,Kai Zhang, Xia Hu, James Caverlee.  A distributed Algorithm for Tensor Completion on Spark,Proceedings of the International Conference on Data Engineering (ICDE 2018).

  22. Liang Lan, Zhuang Wang, Wei Cheng,Kai Zhang*. Scaling up Kernel SVM on Limited Resources:  ALow-rank  Linearization  Approach,IEEE Transactions on Neural Networks and Learning Systems (TNNLS2018).

  23. Xiaohan Zhao, Bo Zong, Ziyu Guan,Kai Zhang, Wei Zhao. Substructure Assembling Network for GraphClassification.Proceedings of the 32th AAAI Conference on Artificial Intelligence (AAAI 2018).

  24. Y Lin, Z Chen, C Cao,  L Tang, K Zhang, W Cheng,  Z Li. Collaborative Alert Ranking for Anomaly Detection. Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM 2018).

  25. Zhang J, Xie X, Rolls ET, Sun J, Zhang K, Jiao Z, Chen Q, Zhang J, Qiu J, Feng J, Neural and GeneticDeterminants of Creativity, NeuroImage, 2018 July 1;(174):164-176.

  26. Jie Zhang, Zhigen Zhao,Kai Zhang, and Zhi Wei, A Feature Sampling Strategy for Analysis of HighDimensional Genomic Data. IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB2018).

  27. Ruihua Cheng, Zhi Wei,Kai Zhang. Network Inference from Contrastive Groups Using DiscriminativeStructural Regularization,SIAM Conference of Data Mining (SDM 2018).

  28. Ping Li, Kaiqi Chen, Yi Ge,Kai Zhangand Michael Small Mining higher-order network structures viamotif-vertex-interactions,Europhysics Letters (EPL 2018).

  29. Kai Zhang, Chuanren Liu, Jie Zhang, Eric Xing, Hui Xiong, Jieping Ye .Randomization or Condensation?:Linear Cost Matrix Sketching Via Cascaded Compression Sampling.Proceedings of the 23rd ACM SIGKDDInternational Conference on Knowledge Discovery and Data Mining (KDD 2017).

  30. Kai Zhang,Jingchao Ni,Wei Cheng,Kai Zhang, Dongjin Song , Tan Yan , Haifeng Chen and Xiang Zhang, RankingCausal Anomalies by Modeling Local Propagations on Networked Systems,IEEE International Conferenceon Data Mining (ICDM 2017).

  31. B. Dong, C. Zheng, H.Wang, L. Tang,K. Zhang, Y. Lin, Z. Li, and H. Chen, Efficient Discovery of Abnor-mal Event Sequences in Enterprise Security Systems,Proceedings of the ACM on Conference on Informationand Knowledge Management (CIKM 2017).

  32. Jie Zhang,  Wei Cheng,  Zhaowen Liu,Kai Zhang*,  Xu Lei,  Ye Yao,  Benjamin Becker,  Yicen Liu,  KeithM. Kendrick, Guangming Lu, Jianfeng Feng.  Neural, electrophsiological and anatomical basis of brain-network variability and its characteristic changes in mental disorders.Brain, 139(8):  2307-2321, 2016.Editor’s choice and featured on the cover of the journal, receiving commentary“TheFlexible Brain”from 2014 MacArther fellow D. S. Bassett.

  33. Shandian Zhe,Kai Zhang, Pengyuan Wang, Kuang-chih Lee, Zenglin Xu, Yuan Qi, Zoubin Ghahramani.Distributed Flexible Nonlinear Tensor Factorization.Proceedings of Neural Information Processing Systems29 (NIPS 2016), Barcelona, Spain.

  34. Kai Zhang, Shandian Zhe, Chaoran Cheng, Zhi Wei, Zhengzhang Chen, Haifeng Chan, Guofei Jiang,Alan Qi, Jieping Ye.  Annealed Sparsity via Adaptive and Dynamic Shrinking.The 22th ACM SIGKDDInternational Conference on Knowledge Discovery and Data Mining (KDD 2016).

  35. Wei Cheng,Kai Zhang, Haifeng Chen, Guofei Jiang, Wei Wang. Ranking Causal Anomalies via Temporaland Dynamical Analysis on Vanishing Correlations.The 22th ACM SIGKDD International Conference onKnowledge Discovery and Data Mining(KDD 2016 Best Paper Award Runner-Up Award).

  36. Ting Chen, Lu-An Tang, Yizhou Sun, Zhengzhang Chen,Kai Zhang. Entity Embedding-based AnomalyDetection  for  Heterogeneous  Categorical  Events.International  Joint  Conference  on  Artificial  Intelligence 2016 (IJCAI 2016) New York City, NY.

  37. Chuanren Liu,Kai Zhang, Hui Xiong, Qiang Yang, Guofei Jiang. Temporal Skeletonization on Sequen-tial Data: Patterns, Categorization, and Visualization.IEEE Transactions on Knowledge and Data Engineering (TKDE), Vol 28, 211–223, 2016.

  38. Liang Lan, Kai Zhang, Hancheng Ge,Wei Cheng,Jun Liu,Andreas Rauber, Xiao-Li Li,Jun Wang, Hongyuan Zha.  Low-rank Decomposition Meets Kernel Learning:  A Generalized Nystr ̈om Method.Artificial Intelligence (AI 2016).

  39. Qiaojun Wang, Kai Zhang, Zhengzhang Chen, Dequan Wang, Guofei Jiang, Ivan Marsic. DesigningLabel-Aware Base Kernels for Semi-supervised Learning. Neural Computing, Vol. 171, No. 1, 1335 – 1343,2016.

  40. Liudmila Ulanova, Tan Yan, Haifeng Chen, Geoff Jiang, Eamonn Keogh,Kai Zhang.  Efficient Long-Term Degradation Profiling in Time Series for Complex Physical Systems.The 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2015), Sydney, Australia, 2015.

  41. Kai Zhang, Liang Lan, James T. Kwok, Vucetic Slobodan, and Bahram Parvin.  Scaling up Graph-basedSemi-supervised Learning Via Prototype Vector Machines.IEEE Transactions on Neural Networks & Learning Systems (TNNLS), Vol. 26, No. 3, 444–457, 2015.

  42. Kai Zhang, Qiaojun Wang, Zhengzhang Chen, Guofei Jiang, Jie Zhang. From Categorical to Numerical:Multiple Transitive Distance Learning and Embedding.SIAM Conference on Data Mining(SDM 2015),Vancouver, Canada.

  43. Kai Zhang,Chuanren Liu, Kai Zhang, Hui Xiong, Qiang Yang, Guofei Jiang. Temporal Skeletonization on SequentialData:  Patterns,  Categorization,  and  Visualization.The  20th  ACM  SIGKDD  International  Conference  onKnowledge Discovery and Data Mining (KDD 2014), New york, USA.

  44. Kai Zhang, Qiaojun Wang, Liang Lan, Yu Sun, Ivan Marsic. Sparse Semi-supervised Learning on Low-rank Kernel,Neural Computing, Vol. 129, No. 10, 265 – 272, 2013.

  45. Kai  Zhang, Vincent W. Zheng, Qiaojun Wang, James T. Kwok, Qiang Yang, Ivan Marsic. Covariate Shift in Hilbert Space: A Solution via Surrogate Kernels. In the30th International Conference on Machine Learning (ICML 2013), Atlanta, Gorgeia.

  46. Kai Zhang, Liang Lan, Jun Liu, Andreas Rauber, Fabian Moerchen. Inductive Kernel Low-rank Decom-position with Priors: A Generalized Nystr ̈om Method. In the29th International Conference on Machine Learning (ICML 2012), Edinburgh, UK.

  47. Kai  Zhang, Liang  Lan, Zhuang Wang, Fabian Moerchen. Scaling Up Kernel SVM on Limited Resources: A Low-rank Linearization Approach.International Conference on Artificial Intelligence and Statistics (AI&STAT 2012), La Palma, Canary Islands.

  48. Kai Zhang, James T. Kwok. Clustered Nystr ̈om Method for Large Scale Manifold Learning and Dimen-sion Reduction,IEEE Transactions on Neural Networks (TNN), 21 (10): 1576-1587, 2010.

  49. Kai Zhang, James T. Kwok. Simplifying Mixture Models through Function Approximation,IEEE Trans-actions on Neural Networks, 21(4): 644 - 658, 2010.

  50. Kai Zhang, James T. Kwok.  Density-Weighted Nystr ̈om Method for Computing Large Kernel Eigen-Systems,Neural Computation, 21(1): 121-146, 2009.

  51. Kai Zhang, Ivor W. Tsang, James T. Kwok.  Maximum Margin Clustering Made Practical,IEEE Transac-tions on Neural Networks (TNN), 20(4): 583-596, 2009.

  52. Kai Zhang, James T. Kwok, Bahram Parvin. Prototype Vector Machine for Large Scale Semi-supervisedLearning. In the26th International Conference on Machine Learning (ICML 2009), Montreal, 2009.

  53. Kai Zhang, Ivor W. Tsang, James T. Kwok. Improved Nystr ̈om Low Rank Approximation and ErrorAnalysis. In the 25th International Conference on Machine Learning (ICML 2008), Helsinki, 2008.

  54. Kai Zhang, Ivor W. Tsang, James T. Kwok.  Maximum Margin Clustering Made Practical.  In the 24th International Conference on Machine Learning (ICML 2007), Oregen, USA, 2007.

  55. Kai  Zhang, James T. Kwok.   Simplifying  Mixture  Models  Through  Function  Approximation.  Neural Information Processing Systems 19 (NIPS 2006), Vancouver, Canada, 2006.

  56. Kai Zhang, James T. Kwok.  Block-Quantized Kernel Matrix for Fast Spectral Embedding.  In the23rd International Conference on Machine Learning (ICML 2006), Pittsburgh, PA, USA, 2006.

  57. Kai Zhang, James T. Kwok, M. Tang. Accelerated Convergence Using Dynamic Mean Shift.  In the 9th European Conference on Computer Vision (ECCV 2006), Graz, Austria.

  58. Ivor W. Tsang, James T. Kwok, Brian Mak,Kai Zhang, Jeffrey J. Pan. Fast Speaker Adaptation via Maximum Penalized Likelihood Kernel Regression.  In the International Conference on Acoustics, Speech, andSignal  Processing (ICASSP  2006). (Best  Paper  Award  from  the  IEEE  Hong  Kong  Chapter  of  Signal Processing Postgraduate Forum)

  59. Kai Zhang, M. Tang, J.T. Kwok.  Applying Neighborhood Consistency for Fast Clustering and KernelDensity Estimation.International Conference on Computer Vision and Pattern Recognition (CVPR 2005).

  60. Zhaowen Liu, Jie Zhang, Kai Zhang, Junying Zhang, Xiaojing Li, Wei Cheng,..., Jianfeng Feng, Tao Li.Distinguishable brain networks relate disease susceptibility to symptom expression in schizophrenia.Human Brain Mapping (HBM 2018) DOI: 10.1002/hbm.24190.

  61. Yan Chen, Ping Li,Kai Zhang, and Jie Zhang.  Finding communities by their centers.Scientific Reports,6:24017, Nature Publishing Group 2016.

  62. Ping Li, Xian Sun, Kai Zhang, Jie Zhang, Jurgen Kurths. The role of structural holes in containing spreading processes.Physical Review E, 93, 032312, 2016.

  63. Haifeng Chen, Mizoguchi Takehiko, Tan Yan, Kai Zhang,  and Geoff Jiang A Quality Control Enginefor  Complex  Physical  Systems.The  45th  IEEE/IFIP  International  Conference  on  Dependable  Systems and Networks(DSN 2015), Rio de Janeiro, Brazil.

  64. Yan Chen, Lixue Chen, Xian Sun,Kai Zhang, Jie Zhang, Ping Li. Coevolutionary dynamics of opinionpropagation and social balance: The key role of small-worldness.The European Physical Journal B, March2014, 87:62.

  65. Ping Li, Xian Sun,Kai Zhang, Jie Zhang. Degree-based attacks are not optimal for desynchronization ingeneral networks,Physical Review E, 88, 022817, 2013.

  66. P. Li,K. Zhang, X. Xu, J. Zhang, M. Small.  Re-examination of explosive synchronization in scale-freenetworks: the effect of disassortativity.Physical Review E, 87, 042803, 2013.

  67. J. Zhang, X. Xu, P. Li,K. Zhang, and M. Small. Node Importance for Dynamical Process on Networks: AMultiscale Characterization,Chaos, 21, 016107, 2011.

  68. J. Zhang, K. Zhang, X. Xu, C.K. Tse and M. Small, Seeding the Kernels in Graphs: towards Multi-Resolution Community Analysis,New Journal of Physics, 11, 113003, 2009.

  69. J. Zhang, J. Sun, X. Luo,K. Zhang, T. Nakamura and M. Small, Characterizing Topology of Pseudoperi-odic Time Series via Complex Network Approach,Physica D, 237(22): 2856-2865, November, 2008.

  70. Kai Zhang, Ju Han, Torsten Groesser, Gerald Fontenay, Bahram Parvin, Inference of Causal Networksfrom Time-Varying Trascriptome Data Via Sparse Coding,Plos ONE, Volume 7, e42306, 2012.

  71. S. Nath, V. Spencer, J. Han, H. Chang,K. Zhang, G. Fontenay, J. Hyman, C. Anderson, M. Hamilton, Y.Chang, and B. Parvin. Identification of Fluorescent Compounds with Non-specific Binding Property via High Throughput Live Cell Microscopy,Plos ONE, Volume 7, Issue 1, e28802, 2012.

  72. Q. Wang,K. Zhang, I. Maarsic and J. K-J Li, Patient Friendly Detection of Early Peripheral Arterial Dis-ease (PAD) by Budgeted Sensor Selection,6th International Conference on Pervasive Computing Technologiesfor Healthcare(PH 2012), San Diego, California, 2012.

  73. Ju Han, Hang Chang, Leandro Loss, Kai Zhang, Fredrick L. Baehner, Joe Gray, Paul Spellman, BahramParvin. Comparison of Sparse Coding and Kernel Methods for Histopathological Classification of Gliobas-toma Multiforme. In theIEEE International Symposium on Biomedical Imaging(ISBI 2011), Chicago, Illinois,U.S. 2011.

  74. Jie Zhang, Kai Zhang, Jianfeng Feng, and Michael Small. Rhythmic Dynamics and Synchronization viaDimensionality Reduction: Application to Human Gait,Plos Computational Biology6(12): e1001033, 2010 (highlighted as featured research).

  75. Kai  Zhang, Joe W. Gray, and Bahram Parvin, Sparse MultiTask Regression for Identifying Common Mechanism of Response to Therapeutic Targets,18th International Conference on Intelligent Systems  forMolecular Biology (ISMB) 2010,Bioinformatics, 26:97-105, 2010

荣誉及奖励

  • 2022年 华东师范大学优秀教职工

  • 2016年 ACM SIGKDD最佳论文提名奖

  • 2016年 NEC Labs America 商业贡献奖

10 访问

相关教师