视频简介

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

研究方向

总方向为机器学习算法与理论,具体聚焦以下几个方面:
--1)大模型学习算法与理论:预训练方法设计与分析、非凸优化理论与算法
--2)图表示学习:图神经网络算法设计、图神经网络理论
--3)大模型自动机器学习理论与算法

学生要求

努力且有激情的学生

毕业学生:
李健(2020毕业),中国科学院信息工程研究所“特聘研究员”(全所唯一);
殷荣(2020毕业),中国科学院信息工程研究所“特聘副研究员”(全所二个);

全部在读学生:
李少杰 (2020级博士生),已发表 ICML 2021、ICML 2022、NeurIPS 2021、ICLR 2022、AAAI 2023、ICLR 2023、IEEE TPAMI 2023、ICML 2023、ECAI 2023 国奖获得者(2次)
胡啸林 (2021级博士生),已发表ICLR 2023
杨杰超 (2021级博士生),已发表CVPR 2023
胡羽蓝 (2021级博士生),已发表ICASSP 2024
朱博炜 (2022级博士生),已发表ACM MM 2021,国奖获得者
唐华镱 (2022级直博生),已发表CVPR 2022、ICML 2022、ICML 2023
姚魏 (2022级直博生),已发表CVPR 2023 (共一)
刘敬宇 (2023级博士),已投稿 ICLR 2024
任芮锋 (2023级博士),已投稿 WWW 2024
龚子瑄 (2023级博士),无
唐鹏威 (2021级硕士),已发表CVPR 2023, MMM 2022, ACML 2023
欧阳晟 (2021级硕士),已发表 AAAI 2023 (共一)、AAAI 2024(参与)、ICASSP(参与)
钱辰(2022级硕士),已投稿 WWW 2023
杨智睿(2022级硕士),已发表 AAAI 2024
李智聪 (2023级硕士),已发表 CVPR 2023(参与)
潘承研 (2023级硕士),无

教授课程

  • 神经网络与深度学习,研究生课程
  • 海量数据挖掘,研究生课程
  • 深度学习导论,本科课程

科研项目

  • 面向多类型多模态图数据的通用大模型技术与药物发现应用研究, 北京市科技计划(中央引导地方专项),2023.9-2025.08, 子课题负责人
  • 面向多场景的大规模异配图表征,58.9万,华为,2023.3-2024.3,负责人
  • 2022年联通研究院面向深度模型的自动机器学习研究技术服务,80万,联通,2022.12-2023.12,负责人
  • 非凸随机优化理论与算法研究, 12万,CCF-华为胡杨林基金,2022.10--2023.9,负责人
  • 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

学术论文

2024
High-dimensional analysis for Generalized Nonlinear Regression: From Asymptotics to Algorithm
Jian Li, Yong Liu*, Weiping Wang
In AAAI

ASWT-SGNN: Adaptive Spectral Wavelet Transform-based Self-Supervised Graph Neural Network
Ruyue Liu, Rong Yin, Yong Liu,Weiping Wang
In AAAI

WaveNet: Tackling Non-Stationary Graph Signals via Graph Spectral Wavelets
Zhirui Yang, Yulan Hu, Sheng Ouyang, Jingyu Liu,Shuqiang Wang, Xibo Ma, Wenhan Wang, Hanjing Su, Yong Liu*
In AAAI
下载: 论文文档

FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning
Jian Li , Yong Liu*, Wei Wang , Haoran Wu, Weiping Wang
In AAAI
下载: 论文文档

GFMAE: Self-Supervised GNN-Free Masked AutoEncoders
Yulan Hu, Sheng Ouyang, Zhirui Yang, Yi Zhao, Junchen Wan, Fuzheng Zhang, Zhongyuan Wang, Yong Liu
ICASSP

2023
Theoretical analysis of divide-and-conquer ERM: From the perspective of multi-view
Yun Liao, Yong Liu*, Shizhong Liao, Qinhua Hu, Jianwu Dang
Information Fusion

Optimal Rates for Agnostic Distributed Learning
Jian Li, Yong Liu*, Weiping Wang
IEEE Transactions on Information Theory

Optimal Convergence for Agnostic Kernel Learning With Random Feature
Jian Li, Yong Liu*, Weiping Wang
IEEE Transactions on Neural Networks and Learning Systems

In-context Learning with Transformer Is Really Equivalent to a Contrastive Learning Pattern
Ruifeng Ren, Yong Liu
Arxiv
下载: 论文文档

Morphological Feature Visualization of Alzheimer's Disease via Multidirectional Perception GAN
Wen Yu, Baiying Lei, Shuqiang Wang, Yong Liu, Zhiguang Feng, Yong Hu, Yanyan Shen, Michael K. Ng
IEEE Transactions on Neural Networks and Learning Systems

Semantic-Aware Dehazing Network With Adaptive Feature Fusion
Shengdong Zhang, Wenqi Ren, Xin Tan, Zhi-Jie Wang, Yong Liu, Jingang Zhang, Xiaoqin Zhang, Xiaochun Cao
IEEE Transactions on Cybernetics

Improving Differentiable Architecture Search via Self-Distillation
Xunyu Zhu, Jian Li, Yong Liu, Weiping Wang
Neural Networks

Towards practical differential privacy in data analysis: Understanding the effect of epsilon on utility in private ERM
Yuzhe Li, Yong Liu, Bo Li, Weiping Wang, Nan Liu
Computers & Security

High Probability Analysis for Non-Convex Stochastic Optimization with Clipping
Shaojie Li, Yong Liu*
In ECAI 2023

Optimal Convergence Rates for Distributed Nystrom Approximation
Jian Li, Yong Liu*, Weiping Wang
Journal of Machine Learning Research
下载: 论文文档

Towards Understanding the Generalization of Graph Neural Networks
Huayi Tang and Yong Liu*
In ICML 2023
下载: 论文文档

Distribution-dependent McDiarmid-type Inequalities for Functions of Unbounded Interaction
Shaojie Li, Yong Liu*
In ICML 2023
下载: 论文文档

Optimal Convergence Rates for Agnostic Nystrom Kernel Learning
Jian Li, Yong Liu*, Weiping Wang
In ICML 2023
下载: 论文文档

Consistency of Multiple Kernel Clustering
Weixuan Liang, Xinwang Liu, Yong Liu, Chuan Ma, Yunping Zhao, Zhe Liu, En Zhu
In ICML 2013

Fair Scratch Tickets: Finding Fair Sparse Networks without Weight Training
Penwei Tang, Wei Yao, Zhicong Li, Yong Liu*
In CVPR 2023
下载: 论文文档

HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search
Jiechao Yang, Yong Liu*
In CVPR 2023
下载: 论文文档

Learning Rates for Nonconvex Pairwise Learning
Shaojie Li, Yong Liu*
IEEE Transactions on Pattern Analysis and Machine Intelligence (CCF A)
下载: 论文文档

Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses
Xiaolin Hu, Shaojie Li, Yong Liu*
In ICLR
下载: 论文文档

Semi-supervised Vector-valued Learning: Improved Bounds and Algorithms
Jian Li, Yong Liu*, Weiping Wang
Pattern Recognition

Understanding the Generalization Performance of Spectral Clustering Algorithms
Shaojie Li, Sheng Ouyang, Yong Liu*
In AAAI 2023 (CCF A)
下载: 论文文档

2022
Scalable Kernel k-Means with Randomized Sketching: From Theory to Algorithm
Rong Yin, Yong Liu*, Xueyan Wang, Weiping Wang, Dan Meng
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022 (CCF A)
下载: 论文文档

Non-IID Federated Learning with Sharper Risk Bound
Bojian Wei, Jian Li, Yong Liu and Weiping Wang
IEEE Transactions on Neural Networks and Learning Systems (SCI 一区)
下载: 论文文档

Convolutional Spectral Kernel Learning with Generalization Guarantees
Jian Li, Yong Liu*, and Weiping Wang
Artificial Intelligence (CCF A)
下载: 论文文档

Fine-Grained Analysis of Stability and Generalization for Modern Meta Learning Algorithms
Jiechao Guan, Yong Liu and Zhiwu Lu
In NeurIPS 2022 (CCF A)
下载: 论文文档

Stability and Generalization of Kernel Clustering: from Single Kernel to Multiple Kernel
Weixuan Liang, Xinwang Liu,Yong Liu,Sihang zhou, Jun-Jie Huang, Siwei Wang, Jiyuan Liu, Yi Zhang, En Zhu
In NeurIPS 2022 (CCF A)
下载: 论文文档

Randomized Sketches for Clustering: Fast and Optimal Kernel $k$-Means
Rong Yin, Yong Liu, Weiping Wang and Dan Meng
In NeurIPS 2022 (CCF A)
下载: 论文文档

Sharper Utility Bounds for Differentially Private Models: Smooth and Non-smooth
康艺霖,刘勇*,李健,王伟平
In CIKM 2022 (CCF B)

基于稳定性分析的非凸在线点对学习的遗憾界
郎璇聪,李春生,刘勇,王梅
计算机研究与发展(第九界中国数据挖掘会议最佳论文)

Non-IID Distributed Learning with Optimal Mixture Weights
Jian Li, Bojian Wei, Yong Liu, Weiping Wang
In ECML 2022 (CCF B)
下载: 论文文档

High Probability Guarantees for Nonconvex Stochastic Gradient Descent with Heavy Tails
Shaojie Li, Yong Liu*
In ICML 2022 (CCF A)
下载: 论文文档

Deep Safe Incomplete Multi-view Clustering: Theorem and Algorithm
Huayi Tang and Yong Liu*
In ICML 2022 (CCF A)

Ridgeless Regression with Random Features
Jian Li , Yong Liu*, Yingying Zhang
In IJCAI 2022 (CCF A)
下载: 论文文档

Deep Safe Multi-view Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase
Huayi Tang, Yong Liu*
CVPR 2022 (CCF A)
下载: 论文文档

High Probability Generalization Bounds for Minimax Problems with Fast Rates
Shaojie Li, Yong Liu*
ICLR 2022
下载: 论文文档

Distributed Randomized Sketching Kernel Learning
Rong Yin, Yong Liu*, Dang Men
AAAI (CCF A)
下载: 论文文档

2021
Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation
Shaogao lv, Junhui Wang, Jiankun Liu, Yong Liu*
In: Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), CCF A, Spotlights (accept rate < 3%))
下载: 论文文档

Towards Sharper Generalization Bounds for Structured Prediction
Shaojie Li, Yong Liu*
In: Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), CCF A
下载: 论文文档

Refined Learning Bounds for Kernel and Approximate $k$-Means
Yong Liu
In: Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), CCF A, Spotlights (accept rate < 3%))
下载: 论文文档

Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN
Wen Yu, Baiying Lei, Yong Liu, Zhiguang Feng, Yong Hu, Yanyan Shen, Shuqiang Wang, Michael K. Ng
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021 (SCI 一区) (To Appear)
下载: 论文文档

Operation-level Progressive Differentiable Architecture Search
Xunyu Zhu, Jian Li, Yong Liu*, Weiping Wang
ICDM 2021
下载: 论文文档

Federated Learning for Non-IID Data: From Theory to Algorithm (Best Student Paper)
Bojian Wei, Jian Li, Yong Liu*, Weiping Wang
Proceedings of the 18th Pacific Rim International Conference on Artificial Intelligence (PRICAI)
下载: 论文文档

General Approximate Cross Validation for Model Selection: Supervised, Semi-supervised and Pairwise Learning
Bowei Zhu, Yong Liu*
Proceedings of The 29th ACM International Conference on Multimedia (ACM MM) (CCF A)
下载: 论文文档

Weighted distributed differential privacy ERM: Convex and non-convex
Yilin Kang, Yong Liu*, Ben Niu, Weiping Wang
Computers & Security (CCF B)
下载: 论文文档
链接: 链接

Distributed Nystrom Kernel Learning with Communications
Rong Yin, Yong Liu, Weiping Wang, Dan Meng
In: Proceedings of the 28th International Conference on Machine Learning (ICML), (CCF A)
下载: 论文文档

Sharper Generalization Bounds for Clustering
Shaojie Li, Yong Liu*
In: Proceedings of the 28th International Conference on Machine Learning (ICML), (CCF A)
下载: 论文文档

Effective Distributed Learning with Random Features: Improved Bounds and Algorithms
Yong Liu, Jiankun Liu, Shuqiang Wang
In: Proceedings of the 9th International Conference on Learning Representations (ICLR)
下载: 论文文档

2020
Extremely sparse Johnson- Lindenstrauss transform: From Theory to Algorithm
Rong Yin, Yong Liu*, Weiping Wang, Dang Men
In: Proceedings of the 20th IEEE International Conference on Data Mining (ICDM), 2020:1376-1381 (CCF B)
下载: 论文文档

Sketch Kernel Ridge Regression using Circulant Matrix: Algorithm and Theory.
Rong Yin, Yong Liu*, Weiping Wang, et al
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 31(9): 3512-3524, 2020 (SCI 一区)
下载: 论文文档

Approximate Kernel Selection via Matrix Approximation.
Lizhong Ding, Shizhong Liao, Yong Liu, Li Liu, Fan Zhu, Yazhou Yao, Ling Shao, Xin Gao
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020. (CCF B)
下载: 论文附件

Automated Spectral Kernel Learning.
Jian Li, Yong Liu*, Weiping Wang
In: Proceedings of 34th Conference on Artificial Intelligence (AAAI), 2020: 4618-4625. (CCF A)
下载: 论文文档

Divide-and-Conquer Learning with Nyström: Optimal Rate and Algorithm
Rong Yin, Yong Liu*, Lijing Lu, Weiping Wang, Dan Meng
Proceedings of 34th Conference on Artificial Intelligence (AAAI), 2020: 6696-6703. (CCF A)
下载: 论文文档

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 (TPAMI), 2020,42(5):1083-1096. (CCF A)
下载: 论文附件

2019
Kernel Stability for Model Selection in Kernel-based Algorithms.
Yong Liu, Shizhong Liao, Hua Zhang, et al
IEEE Transactions on Cybernetics (TCYB), 2019. Online, DOI: 10.1109/TCYB.2019. 2923824. (SCI一区)
下载: 论文附件

Approximate Kernel Selection with Strong Approximate Consistency.
Lizhong Ding, Yong Liu, Shizhong Liao, Yu Li, Peng Yang, Yijie Pan, Chao Huang, Ling Shao, Xin Gao
In: Proceedings of 33th Conference on Artificial Intelligence (AAAI), 2019: 3462-3469.
下载: 论文附件

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
In: Proceedings of 33th Conference on Artificial Intelligence (AAAI), 2019:3454-3461.
下载: 论文附件

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
IEEE Transactions on Image Processing (TIP), 2019, 28(9):4486-4499. (CCF A)
下载: 论文附件

Approximate Manifold Regularization: Scalable Algorithm and Generalization Analysis.
Jian Li, Yong Liu*, Rong Yin, et al
In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019:2887-2893. (CCF A)
下载: 论文文档

Multi-Class Learning using Unlabeled Samples: Theory and Algorithm.
Jian Li, Yong Liu*, Rong Yin , Weiping Wang
Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019: 2880-2886. (CCF A))
下载: 论文文档

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
Advances in Neural Information Processing Systems 32 (NeurIPS), 2019:11257-11268. (CCF A)
下载: 论文附件

2018
Randomized Kernel Selection With Spectra of Multilevel Circulant Matrices.
Lizhong Ding, Shizhong Liao, Yong Liu, Peng Yang, Xin Gao
Proceedings of 32rd Conference on Artificial Intelligence (AAAI), 2018: 2910-2917.

Fast Cross-Validation.
Yong Liu, Hailun Lin, Lizhong Ding, et al
In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), 2910-2917, 2018. (CCF A)
下载: 论文附件

Multi-Class Learning: From Theory to Algorithm.
Jian Li, Yong Liu*, Rong Yin, et al
Advances in Neural Information Processing Systems 31 (NeurIPS), 1593-1602, 2018. (CCF A)
下载: 论文文档

2017
Granularity selection for cross-validation of SVM.
Yong Liu, Shizhong Liao
Information Sciences, 2017, 475-483. ( CCF B)
下载: 论文附件

Efficient Kernel Selection via Spectral Analysis.
Jian Li, Yong Liu, Hailun Lin
In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI), 2017: 2124-2130. (CCF A)
下载: 论文附件

Infinite Kernel Learning: Generalization Bounds and Algorithms.
Yong Liu, Shizhong Liao, Hailun Lin, et al
In: Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), 2017, 2280-2286. (CCF A)
下载: 论文附件

Generalization Analysis for Ranking Using Integral Operator,
Yong Liu, Shizhong Liao, Linhai Lun, et al
In: Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), 2017: 2273-2279. (CCF A)
下载: 论文附件

2016
基于积分算子空间显示描述的框架核选择方法
刘勇,廖士中
中国科学: 信息科学, 2016, 46(2), 165–178. (CCF A 中文期刊)
下载: 论文附件

2015
Eigenvalues ratio for kernel selection of kernel methods
Yong Liu, Shizhong Liao
In: Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI), 2015: 2814–2820. (CCF A)
下载: 论文附件

2014
Preventing Over-Fitting of Cross-Validation with Kernel Stability
Yong Liu, Shizhong Liao
In: Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML), 2014:290–305. (CCF B)
下载: 论文附件

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,2014, 51(10):2171-2177. (CCF A 中文期刊)
下载: 论文附件

Kernel selection with spectral perturbation stability of kernel matrix
Yong Liu, Shizhong Liao
Science China Information Sciences, 2014, 57: 112103(10) (CCF B)
下载: 论文附件

Efficient Approximation of Cross-validation for Kernel Methods using Bouligand Influence Function
Yong Liu, Shali Jiang, Shizhong Liao
In: Proceedings of The 31st International Conference on Machine Learning (ICML). 2014, 324-332. (CCF A)
下载: 论文附件

2013
Eigenvalues Perturbation of Integral operator for Kernel Selection
Yong Liu, Shali Jiang, Shizhong Liao
In: Proceedings of the 22nd ACM International Conference on Information and Knowledge management (CIKM), 2013:2189-2198. (CCF B)
下载: 论文附件

2011
Learning kernels with upper bounds of leave-one-out error
Yong Liu*, Shizhong Liao, Yuexuan-Hou
In: Proceedings of the 20th ACM International Conference on Information and Knowledge management (CIKM), 2011:2205-2208. (CCF B)
下载: 论文文档

荣誉奖励

  • 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

社会兼职

  • AAAI 2021 高级程序委员
  • IJCAI 2020,IJCAI 2019 高级程序委员
  • NeurIPS 2020, 2021, 程序委员
  • AAAI 2020,程序委员
  • ICML 2019, 2020, 2021,程序委员
  • ICLR 2021,程序委员

contact

电话:--

邮箱:liuyonggsai@ruc.edu.cn

个人网页:https://iie-liuyong.github.io/

办公地址:北京市海淀区中关村中国人民大学立德楼1716