中文简介

刘勇 男,副教授,博导, 中国人民大学高瓴人工智能学院

电子邮箱:liuyonggsai@ruc.edu.cn

主页:https://gsai.ruc.edu.cn/addons/teacher/index/info.html?user_id=16&ruccode=20200136&ln=cn

中国人民大学,准聘副教授、博士生导师。博士毕业于天津大学。从事机器学习研究,特别关注大规模机器学习、自动机器学习、统计机器学习理论等。在顶级期刊和会议上发表论文40余篇,其中以第一作者或通讯作者发表CCF A类文章30余篇,涵盖机器学习领域顶级期刊TPAMI、TIP、TNNLS、TCBY和ICML,NeurIPS,ICLR,IJCAI,AAAI机器学习5大顶级会议。曾获得中国科学院“青年创新促进会”会员(院人才)以及中国科学院信息工程研究所“引进优秀人才”称号。担任国际顶级会议IJCAI高级程序委员,NeurIPS、ICML、AAAI、ECAI等程序委员。主持多项科研基金项目,包括国家自然科学基金青年基金、面上项目、中国科学院基础前沿科学研究计划、腾讯犀牛鸟基金、联通联合项目、华为联合项目等。

研究方向

大规模机器学习,模型选择,统计机器学习理论

教育背景

  • 2011-2016,天津大学计算机应用专业,博士生,导师:廖士中
  • 2009-2011,天津大学计算机科学与技术专业,硕士生,导师:廖士中

工作经历

  • 中国人民大学高瓴人工智能学院,准聘副教授,副研究员,2021年7月至今
  • 中国人民大学高瓴人工智能学院,副研究员,准聘助理教授, 2020年8月-2021年7月
  • 中国科学院信息工程研究所,副研究员,2018年10月-2020年7月
  • 中国科学院信息工程研究所,助理研究员,2016年7月-2018年10月

荣誉称号

  • 2021年 Best Student Paper PRICAI 2021
  • 2019年中国科学院“青促会”人才称号
  • 2017年中国科学院信息工程研究所“引进优秀人才”称号
  • 2012年博士研究生国家学术新人奖
  • Best Paper Award of The 2nd PAKDD Doctoral Symposium on Data Mining

主持项目

  • 基于图神经网络的反事实欺诈检测算法研究, 30万,腾讯微信支付犀牛鸟专项, 2022.5-2023.5,负责人
  • 大规模半监督核学习的模型选择理论与算法研究, 20万,北京市自然科学基金面上项目,2022.1-2024.12, 负责人
  • 大规模实时用户表征,40万,华为,2022.1-2023.1,负责人
  • 面向联通应用场景的自动机器学习,20万,联通,2021.11-2022.3,负责人
  • 大规模深度核学习的理论与算法研究, 59万,国家自然科学基金面上项目,2021.1-2024.12,负责人
  • 大规模核方法积分算子谱分析的模型选择方法,国家自然科学基金青年项目,24万,2018.1-2020.12,负责人
  • 深度神经网络结构自动搜索理论与算法研究,90万,中国科学院基础前沿科学研究计划,2019.9-2024.9,负责人
  • 大规模机器学习模型选择算法研究,中国科学院“青促会”人才项目,80万,2019.1-2022.12,负责人
  • 基于积分算子谱分析的核方法模型选择,中国科学院信息工程研究所, 引进优秀青年人才,40万,2017.1-2019.12,负责人
  • 基于贝叶斯优化的DNN模型结构自动机器学习,2019.10-2020.9,15万,腾讯犀牛鸟基金 (获得优秀),负责人
  • 大数据和人工智能发展现状及趋势,保密局战略研究项目子课题,40万,2017.9-2020.12,子课题负责人

文章列表

———2022———

Non-IID Distributed Learning with Optimal Mixture Weights
Jian Li, Xuanyu Zhu, Yong Liu*. In ECML, 2022

High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails
Shaojie Li, Yong Liu*. In ICML, 2022

Deep Safe Incomplete Multi-view Clustering: Theorem and Algorithm
Huayi Tang, Yong Liu*. In ICML, 2022

Understanding the Generalization Performance of Spectral Clustering Algorithms
Shaojie Li, Sheng Ouyang, Yong Liu*. In IJCAI, 2022

Optimal Rates for Distributed Learning with Random Features
Jian Li, Yong Liu*. In IJCAI, 2022

Ridgeless Regression with Random Features
Jian Li , Yong Liu*, Yingying Zhang. In IJCAI, 2022

Deep Safe Multi-view Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase
Huayi Tang, Yong Liu*. In CVPR, 2022

High Probability Generalization Bounds for Minimax Problems with Fast Rates
Shaojie Li, Yong Liu*. In ICLR, 2022

Distributed Randomized Sketching Kernel Learning
Rong Yin, Yong Liu*, Dang Men. In AAAI, 2022

———2021———

Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation
Shaogao lv, Junhui Wang, Jiankun Liu, Yong Liu*. In NeurIPS, 2021

Towards Sharper Generalization Bounds for Structured Prediction
Shaojie Li, Yong Liu*. In NeurIPS, 2021

Refined Learning Bounds for Kernel and Approximate kmeans
Yong Liu*. In NeurIPS, 2021

Operation-level Progressive Differentiable Architecture Search
Xunyu Zhu, Jian Li, Yong Liu*, Weiping Wang. In ICDM, 2021

Federated Learning for Non-IID Data: From Theory to Algorithm (Best Student Paper)
Bojian Wei, Jian Li, Yong Liu*, Weiping Wang. In PRICAI, 2021

General Approximate Cross Validation for Model Selection: Supervised, Semi-supervised and Pairwise Learning
Bowei Zhu, Yong Liu*. In ACM MM, 2021

Weighted Distributed Differential Privacy ERM: Convex and Non-convex
Yilin Kang, Yong Liu*, Ben Niu, Weiping Wang. Computers & Security, 2021

Distributed Nystrom Kernel Learning with Communications
Rong Yin, Yong Liu, Weiping Wang, Dan Meng. In ICML, 2021

Sharper Generalization Bounds for Clustering
Shaojie Li, Yong Liu*. In ICML, 2021

Effective Distributed Learning with Random Features: Improved Bounds and Algorithms
Yong Liu* iankun Liu, Shuqiang Wang. In ICLR, 2021

———2020———

Extremely sparse Johnson- Lindenstrauss transform: From Theory to Algorithm
Rong Yin, Yong Liu*, Weiping Wang, Dang Men. In ICDM,2020

Sketch Kernel Ridge Regression using Circulant Matrix: Algorithm and Theory
Rong Yin, Yong Liu*, Weiping Wang. IEEE Transactions on Neural Networks and Learning Systems, 2020

Automated Spectral Kernel Learning
Jian Li, Yong Liu*, Weiping Wang. In AAAI, 2020

Divide-and-Conquer Learning with Nystrom: Optimal Rate and Algorithm
Rong Yin, Yong Liu*, Lijing Lu, Weiping Wang, Dan Meng. In AAAI, 2020

Fast Cross-Validation for Kernel-based Algorithms
Yong Liu*, Shizhong Liao, Shali Jiang, Lizhong Ding, Hailun Lin, Weiping Wang. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019

———2019———

Kernel Stability for Model Selection in Kernel-based Algorithms
Yong Liu*, Shizhong Liao, Hua Zhang. IEEE Transactions on Cybernetics, 2019

Learning Structural Representations via Dynamic Object Landmarks Discovery for Sketch Recognition and Retrieval
Hua Zhang, Peng She, Yong Liu, Jianhou Gan, Xiaochun Cao, Hassan Foroosh. In IEEE TIP, 2019

Approximate Manifold Regularization: Scalable Algorithm and Generalization Analysis
Jian Li, Yong Liu*, Rong Yin. In IJCAI, 2019

Multi-Class Learning using Unlabeled Samples: Theory and Algorithm
Jian Li, Yong Liu*, Rong Yin , Weiping Wang. In IJCAI, 2019

Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test
Lizhong Ding, Mengyang Yu, Li Liu, Fan Zhu, Yong Liu, Yu Li, Ling Shao. In NeurIPS, 2019

———2018———

Randomized Kernel Selection With Spectra of Multilevel Circulant Matrices
Lizhong Ding, Shizhong Liao, Yong Liu, Peng Yang, Xin Gao. In AAAI, 2018

Max-Diversity Distributed Learning: Theory and Algorithms
Yong Liu, Jian Li, Weiping Wang. arXiv, 2018.

Multi-Class Learning: From Theory to Algorithm
Jian Li, Yong Liu*, Rong Yin, Hua Zhang, Li-zhong Ding, Weiping Wang. Advances in Neural Information Processing Systems 31 (NIPS), 2018, accept.

———2017———

Fast Cross-Validation
Yong Liu, Hailun Lin, Lizhong Ding, Weiping Wang, Shizhong Liao. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), 2910-2917, 2018

Generalization Analysis for Ranking Using Integral Operator
Yong Liu, Shizhong Liao, Hailun Lin, Yinliang Yue, Weiping Wang. Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), 2272-2279, 2017

Infinite Kernel Learning: Generalization Bounds and Algorithms
Yong Liu, Shizhong Liao, Hailun Lin, Yinliang Yue, Weiping Wang. Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), 2280-2286, 2017

Efficient Kernel Selection via Spectral Analysis
Jian Li, Yong Liu*, Hailun Lin, Yinliang Yue, Weiping Wang. Procedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), 2124-2130, 2017.

———2015———

Eigenvalues Ratio for Kernel Selection of Kernel Methods
Yong Liu, Shizhong Liao. Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI), 2814-2820, 2015

———2014———

Efficient Approximation of Cross-Validation for Kernel Methods using Bouligand influence function
Yong Liu, Shali Jiang, Shizhong Liao. Proceedings of the 31st International Conference on Machine Learning (ICML), 324-332, 2014

Approximate Kernel Selection with Strong Approximate Consistency
Lizhong Ding, Yong Liu, Shizhong Liao, Peng Yang, Yu Li, Yijie Pan, Chao Huang, Ling Shao, Xin Gao. Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), 2019, accept.

Linear Kernel Tests via Empirical Likelihood for High Dimensional Data
Lizhong Ding, Zhi Liu, Yu Li, Shizhong Liao, Yong Liu, Peng Yang, Ge Yu, Ling Shao, Xin Gao. Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), 2019, accept.

Randomized Kernel Selection With Spectra of Multilevel Circulant Matrices
Li-Zhong Ding, Shizhong Liao, Yong Liu, Peng Yang, Xin Gao. Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI), 2497-2503, 2018

Granularity Selection for Cross-Validation of SVM
Yong Liu, Shizhong Liao. Information Sciences, 378:475-483, 2017

Learning Entity and Relation Embeddings for Knowledge Resolution
Hailun Lin, Yong Liu*, Weiping Wang, Yinliang Yue, Zheng Lin. Procedia Computer Science, 108:345-354, 2017

Preventing Over-Fitting of Cross-Validation with Kernel Stability
Yong Liu, Shizhong Liao. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML), 290-305, 2014

Kernel Selection with Spectral Perturbation Stability of Kernel Matrix
Yong Liu, Shizhong Liao. Science China Information Sciences 57(11):1-10, 2014

Error Analysis for Vector-Valued Regularized Least-Squares Algorithm
Yong Liu, Shizhong Liao. Proceedings on the International Conference on Artificial Intelligence (ICAI), 2014

Eigenvalues Perturbation of Integral Operator for Kernel Selection
Yong Liu, Shali Jiang, Shizhong Liao. Proceedings of the 22nd ACM international Conference on Information and Knowledge Management (CIKM), 2189-2198, 2013

An Explicit Description of the Extended Gaussian Kernel
Yong Liu, Shizhong Liao. Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, 88-99, 2012 (Best Paper)

Learning Kernels with Upper Bounds of Leave-One-Out error
Yong Liu, Shizhong Liao, Yuexian Hou. Proceedings of the 20th ACM international Conference on Information and Knowledge Management (CIKM), 2205-2208, 2011

An Error Bound for Eigenvalues of Graph Laplacian with Bounded Kernel Function
Yong Liu, Shizhong Liao. Proceedings of Seventh International Conference on Computational Intelligence and Security (CIS), 435-440, 2011

Kernel Construction via Generalized Eigenvector Decomposition
Yong Liu, Shizhong Liao. Foundations of Intelligent Systems, 191-200, 2011

基于近似高斯核显式描述的大规模SVM求解
刘勇, 江沙里, 廖士中. 计算机研究与发展, 51(10):2171-2177, 2014

基于积分算子空间显式描述的框架核选择方法
刘勇, 廖士中. 中国科学:信息科学, 46(2):165-178, 2016

基于支持向量机泛化误差界的多核学习方法
刘勇, 廖士中. 武汉大学学报(理学版), 58(2), 2012