尚凡华

英才教授、博导

单位：天津大学智能与计算学部

邮箱：fhshang@tju.edu.cn

地址：天津市津南区雅观路135号天津大学北洋园校区55楼B207

邮编：300350

个人简介：

尚凡华，英才教授，硕士/博士研究生导师。现为天津大学 智能与计算学部 计算机科学与技术学院 教授。已在IEEE TPAMI、IEEE TNNLS、IEEE TKDE等顶级期刊和ICML、NeurIPS/NIPS、KDD、AAAI、IJCAI、VLDB、ACM MM等顶级国际会议上发表学术论文近100篇，并与国际上多个顶尖科研团队(包括美国康奈尔大学、University of Texas at Austin、新加坡国立大学、南洋理工大学、香港中文大学等)具有良好的长期合作关系。担任包括NeurIPS/NIPS、ICML、ICLR、CVPR、ICCV、AAAI、IJCAI、KDD等机器学习、计算机视觉、人工智能、数据挖掘等领域顶级国际会议的程序委员会委员及Senior PC，还担任20多个国际学术期刊(例如TPAMI、TNNLS、TKDE、TSP、TIP等)审稿人。2015年获得陕西省优秀博士学位论文奖，2018年入选“华山菁英人才计划”，2022年入选“北洋学者英才计划”。

工作与学习经历：

·        2022年 --  至今， 天津大学 智能与计算学部，英才教授、博士生导师

·        2018年 -- 2022年，西安电子科技大学，菁英教授、博士生导师

·        2016年 -- 2018年，香港中文大学，副研究员

·        2013年 -- 2015年，香港中文大学，博士后研究员

·        2012年 -- 2013年，美国 杜克大学，博士后

·        2007年 -- 2012年，西安电子科技大学，博士

研究领域：

机器学习、深度学习、计算机视觉

研究方向：

优化算法及理论、图像/视频处理、并行/分布式计算、隐私保护与联邦学习

招生信息：

       每年招收计算机、人工智能、电子信息、数学等相关专业的硕士生和博士研究生，欢迎有志从事机器学习、视频计算等方向的学生加入本课题组。课题组科研经费充足，为科研项目的开展提供充足的硬件支持。非常欢迎优秀的本科生加入我们课题组，包括课题研究或毕业设计，培养自己的研究兴趣和研究方向。Email发送到fhshang@tju.edu.cn，会在三天内回复。

代表性论文：

(*通讯作者，2021年影响因子，更多信息请看英文主页：https://sites.google.com/site/fanhua217/publications)

§  Yuanyuan Liu, Fanhua Shang*, Hongying Liu, Lin Kong, Licheng Jiao, Zhouchen Lin. "Accelerated Variance Reduction Stochastic ADMM for Large-Scale Machine Learning". IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 43(12): 4242-4255, 2021. (SCI 1区, IF: 24.314, CCF A)

§  Fanhua Shang, James Cheng, Yuanyuan Liu, Zhi-Quan Luo, and Zhouchen Lin. "Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications". IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 40(9): 2066-2080, 2018. (SCI 1区, IF: 24.314, CCF A)

§  Yuanyuan Liu, Fanhua Shang*, Weixin An, Hongying Liu, Zhouchen Lin. “Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots”. In: Proceedings of International Conference on Machine Learning (ICML), pp. 14008-14035, 2022. (CCF A)

§  Kaiwen Zhou, Fanhua Shang*, James Cheng. "A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates". In: Proceedings of International Conference on Machine Learning (ICML), pp. 5975-5984, 2018. (CCF A)

§  Yuanyuan Liu, Fanhua Shang*, James Cheng, Hong Cheng, Licheng Jiao. "Accelerated First-order Methods for Geodesically Convex Optimization on Riemannian Manifolds". In: Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS), pp. 4875-4884, 2017. (CCF A)

2022:

§  Yuanyuan Liu, Fanhua Shang*, Weixin An, Hongying Liu, Zhouchen Lin. “Kill a Bird with Two Stones: Closing the Convergence Gaps in Non-Strongly Convex Optimization by Directly Accelerated SVRG with Double Compensation and Snapshots”. In: Proceedings of International Conference on Machine Learning (ICML), pp. 14008-14035, 2022. (CCF A)

§  Qing Sun, Fan Lyu, Fanhua Shang, Wei Feng, Liang Wan. "Exploring Example Influence in Continual Learning". To appear in Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), 2022. (CCF A)

§  Dong Wang, Yicheng Liu, Liangji Fang, Fanhua Shang*, Yuanyuan Liu, Hongying Liu. “Balanced Gradient Penalty Improves Deep Long-Tailed Learning.” To appear in Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022. (CCF A)

§  Weixin An, Yingjie Yue, Yuanyuan Liu, Fanhua Shang*, Hongying Liu. “A Numerical DEs Perspective on Unfolded Linearized ADMM Networks for Inverse Problems.” To appear in Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022. (CCF A)

§  Fanhua Shang, Bingkun Wei, Hongying Liu, Yuanyuan Liu, Pan Zhou and Maoguo Gong. “Efficient Gradient Support Pursuit with Less Hard Thresholding for Cardinality-Constrained Learning”. To appear in IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022. (SCI 1区, IF: 14.255)

§  Yuanyuan Liu, Jiacheng Geng, Fanhua Shang*, Weixin An, Hongying Liu, Qi Zhu, Wei Feng. “Laplacian Smoothing Stochastic ADMMs with Differential Privacy Guarantees”. IEEE Transactions on Information Forensics and Security (TIFS), 17: 1814-1826, 2022. (SCI 1区, IF: 7.231, CCF A)

§  Fanhua Shang, Hua Huang, Jun Fan, Hongying Liu, Yuanyuan Liu, Jianhui Liu. “Asynchronous Parallel, Sparse Approximated SVRG for High-Dimensional Machine Learning”. To appear in IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022. (SCI 1区, IF: 9.235, CCF A)

§  Yuanyuan Liu, Jiacheng Geng, Fanhua Shang*, Hongying Liu, Qi Zhu. “Loopless Variance Reduced Stochastic ADMM forEquality Constrained Problems in IoT Applications”. IEEE Internet of Things Journal (IOT), 9(3): 2293-2303, 2022. (SCI 1区, IF: 10.238)

§  Lin Kong, Wei Sun, Fanhua Shang*, Yuanyuan Liu, Hongying Liu. “HNO: High-order Numerical Architecture for ODE-Inspired Deep Unfolding Networks”. In: Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), pp. 7220-7228, 2022. (CCF A, Full oral paper)

§  Hongying Liu, Zhubo Ruan, Peng Zhao, Chao Dong, Fanhua Shang*, Yuanyuan Liu, Linlin Yang. “Video Super Resolution Based on Deep Learning: A Comprehensive Survey”. To appear in Artificial Intelligence Review (AIR), 2022. (SCI 1区, IF: 9.588)

§  Qigong Sun, Licheng Jiao, Yan Ren, Xiufang Li, Fanhua Shang, Fang Liu. “Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization.” To appear in IEEE Transactions on Cybernetics (TC), 2022. (SCI 1区, IF: 19.118)

2021：

§  Yuanyuan Liu, Fanhua Shang*, Hongying Liu, Lin Kong, Licheng Jiao, Zhouchen Lin. "Accelerated Variance Reduction Stochastic ADMM for Large-Scale Machine Learning". IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 43(12): 4242-4255, 2021. (SCI 1区, IF: 24.314, CCF A)

§  Fanhua Shang, Tao Xu, Yuanyuan Liu, Hongying Liu, Longjie Shen, Maoguo Gong. “Differentially Private ADMM Algorithms for Machine Learning”. IEEE Transactions on Information Forensics and Security (TIFS), 16: 4733-4745, 2021. (SCI 1区, IF: 7.231, CCF A)

§  Hua Huang, Fanhua Shang*, Yuanyuan Liu, Hongying Liu. “Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning”. In: Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI), pp. 2556-2562, 2021. (CCF A)

§  Hongying Liu, Ruyi Luo, Fanhua Shang*, Mantang Niu, Yuanyuan Liu. “Progressive Semantic Matching for Video-Text Retrieval”. In: Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), pp. 5083-5091, 2021. (CCF A)

§  Yangyang Li, Lin Kong, Fanhua Shang*, Yuanyuan Liu, Hongying Liu, Zhouchen Lin. “Learned Extragradient ISTA with Interpretable Residual Structures for Sparse Coding”. In: Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), pp. 8501-8509, 2021. (CCF A)

§  Hongying Liu, Peng Zhao, Zhubo Ruan, Fanhua Shang*, Yuanyuan Liu. “Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling”. In: Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), pp. 2127-2135, 2021. (CCF A)

§  Ronghua Shang, Lujuan Wang, Fanhua Shang, Licheng Jiao, Yangyang Li. “Dual space latent representation learning for unsupervised feature selection”. Pattern Recognition (PR), 114:107873, 2021. (SCI 1区, IF: 8.518)

§  Fanhua Shang, Kaiwen Zhou, Hongying Liu, James Cheng, Ivor Tsang, Lijun Zhang, Dacheng Tao, Licheng Jiao. "VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning". IEEE Transactions on Knowledge and Data Engineering (TKDE), 32(1): 188-202, 2021. (SCI 1区, IF: 9.235, CCF A)

§  Yang Meng, Ronghua Shang, Fanhua Shang, Licheng Jiao, Shuyuan Yang, Rustam Stolkin. “Semi-supervised Graph Regularized Deep Non-negative Matrix Factorization with Bi-orthogonal Constraints for Data Representation”. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021. (SCI 1区, IF: 14.255)

§  Hengmin Zhang, Feng Qian, Fanhua Shang, Wenli Du, Jianjun Qian, Jian Yang. “Global Convergence Guarantees of (A)GIST for a Family of Noncovex Sparse Learning Problems.” IEEE Transactions on Cybernetics (TC), 52(5): 3276-3288, 2021. (SCI 1区, IF: 19.118)