Dr. Jinfeng Yi
Vice President, Head of AI and Data Science
4Paradigm Technology
jinfengyi [DOT] ustc [AT] gmail [DOT] com
About
I am the Corporate Vice President at 4Paradigm Technology, a Hong Kong-listed leading AI company renowned for AI-driven decision-making and enterprise AI solutions. In this role, I oversee the company's core AI division, leading teams across all AI disciplines—from large generative models to machine learning, computer vision, speech, and natural language processing. Previously, I was a Senior Director at JD.com, where I led the Machine learning Department and JD AI Research (Shanghai).
In addition to my corporate responsibilities, I serve as an Adjunct Professor at Fudan University, Renmin University of China, and the University of Science and Technology of China. I have published nearly 100 papers in prestigious AI conferences and journals, accumulating over 10,000 citations. Furthermore, I regularly serve as an Area Chair for top conferences like NeurIPS and ICML.
I have received the MIT TR35 China Award and the Management Science Innovation Award. I was also honored with JD's highest award, the "CEO Special Award", and is the only individual recipient among over 360,000 employees. Furthermore, I have received two of the company's most prestigious technical awards: the "Outstanding Achievement Gold Award" and the "Technology Innovation Gold Award."
Research Interest
I am broadly interested in understanding and tackling complex real-world problems through the lens of data-driven artificial intelligence. Recently, I am particularly interested in the following research topics:
Adversarial Machine Learning and Trustworthy AI
Recommendation and Demand Matching
Large Generative Models for High Stakes Applications
Collective Intelligence and Crowdsourcing
Recent Services
Area Chair: ICML 2024, 2023
Area Chair: NeurIPS 2023, 2022, 2021
Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards
Bo Xue, Yimu Wang, Yuanyu Wan, Jinfeng Yi, and Lijun Zhang. In NeurIPS 2023
FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks
Bingqing Song, Prashant Khanduri, Xinwei Zhang, Jinfeng Yi, and Mingyi Hong. In ICML 2023
Training Meta-Surrogate Model for Transferable Adversarial Attack
Yunxiao Qin, Yuanhao Xiong, Jinfeng Yi, and Cho-Jui Hsieh. In AAAI 2023
Stochastic Graphical Bandits with Heavy-Tailed Rewards
Yutian Gou, Jinfeng Yi, and Lijun Zhang. In UAI 2023
With False Friends Like These, Who Can Notice Mistakes?
Lue Tao, Lei Feng, Jinfeng Yi, and Songcan Chen. In AAAI 2022
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jinfeng Yi, Mingyi Hong, Shiyu Chang, and Sijia Liu. In ICLR 2022
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
Xinwei Zhang, Xiangyi Chen, Mingyi Hong, Steven Wu, and Jinfeng Yi. In ICML 2022
A Simple yet Universal Strategy for Online Convex Optimization
Lijun Zhang, Guanghui Wang, Jinfeng Yi, and Tianbao Yang. In ICML 2022
Can Adversarial Training Be Manipulated By Non-Robust Features?
Lue Tao, Lei Feng, Hongxin Wei, Jinfeng Yi, Sheng-Jun Huang, and Songcan Chen. In NeurIPS 2022
Smoothed Online Convex Optimization Based on Discounted-Normal-Predictor
Lijun Zhang, Wei Jiang, Jinfeng Yi, and Tianbao Yang. In NeurIPS 2022
Adaptive Feature Generation for Online Continual Learning from Imbalanced Data
Yingchun Jian, Jinfeng Yi, Lijun Zhang. PAKDD 2022
Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System
Tianxin Wei, Fuli Feng, Jiawei Chen, Ziwei Wu, Jinfeng Yi, and Xiangnan He. In KDD 2021
Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
Sanshi Yu, Zhuoxuan Jiang, Dongdong Chen, Shanshan Feng, Dongsheng Li, Qi Liu, and Jinfeng Yi. In KDD 2021
Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
Lue Tao, Lei Feng, Jinfeng Yi, Sheng-Jun Huang, and Songcan Chen. In NeurIPS 2021
Fast Certified Robust Training with Short Warmup
Zhouxing Shi, Yihan Wang, Huan Zhang, Jinfeng Yi, and Cho-Jui Hsieh. In NeurIPS 2021
Hierarchical Personalized Federated Learning for User Modeling
Jinze Wu, Qi Liu, Zhenya Huang, Yuting Ning, Hao Wang, Enhong Chen, Jinfeng Yi, and Bowen Zhou. In WWW 2021
Spanning attack: reinforce black-box attacks with unlabeled data.
Lu Wang, Huan Zhang, Jinfeng Yi, Cho-Jui Hsieh, and Yuan Jiang. Machine Learning 2020
A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks
Jinghui Chen, Dongruo Zhou, Jinfeng Yi, and Quanquan Gu. In AAAI 2020
Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
Minhao Cheng, Jinfeng Yi, Pin-Yu Chen, Huan Zhang, and Cho-Jui Hsieh. In AAAI 2020
Potential Passenger Flow Prediction: A Novel Study for Urban Transportation Development
Yongshun Gong, Zhibin Li, Jian Zhang, Wei Liu, and Jinfeng Yi. In AAAI 2020
Improving Adversarial Robustness Requires Revisiting Misclassified Examples
Yisen Wang, Difan Zou, Jinfeng Yi, James Bailey, Xingjun Ma, and Quanquan Gu. In ICLR 2020
Provably Robust Metric Learning
Lu Wang, Xuanqing Liu, Jinfeng Yi, Yuan Jiang, and Cho-Jui Hsieh. In NeurIPS 2020
AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks
Chun-Chen Tu, Pai-Shun Ting, Pin-Yu Chen, Sijia Liu, Huan Zhang, Jinfeng Yi, Cho-Jui Hsieh, Shin-Ming Cheng. In AAAI 2019
How You Act Tells a Lot: Privacy-Leaking Attack on Deep Reinforcement Learning
Xinlei Pan, Weiyao Wang, Xiaoshuai Zhang, Bo Li, Jinfeng Yi, and Dawn Song. In AAMAS 2019
Symmetric Cross Entropy for Robust Learning With Noisy Labels
Yisen Wang, Xingjun Ma, Zaiyi Chen, Yuan Luo, Jinfeng Yi, and James Bailey. In ICCV 2019
AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos
Chaowei Xiao, Ruizhi Deng, Bo Li, Taesung Lee, Benjamin Edwards, Jinfeng Yi, Dawn Song, Mingyan Liu, and Ian M. Molloy. In ICCV 2019
Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged Solutions
Zaiyi Chen, Zhuoning Yuan, Jinfeng Yi, Bowen Zhou, Enhong Chen, and Tianbao Yang. In ICLR 2019
Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach
Minhao Cheng, Thong Le, Pin-Yu Chen, Huan Zhang, Jinfeng Yi, and Cho-Jui Hsieh. In ICLR 2019
On the Convergence and Robustness of Adversarial Training.
Yisen Wang, Xingjun Ma, James Bailey, Jinfeng Yi, Bowen Zhou, and Quanquan Gu. In ICML 2019
Similarity Preserving Representation Learning for Time Series Clustering
Qi Lei, Jinfeng Yi, Roman Vaculín, Lingfei Wu, and Inderjit S. Dhillon. In IJCAI 2019
Improving the Robustness of Deep Neural Networks via Adversarial Training with Triplet Loss
Pengcheng Li, Jinfeng Yi, Bowen Zhou, and Lijun Zhang. In IJCAI 2019
Sample Adaptive Multiple Kernel Learning for Failure Prediction of Railway Points
Zhibin Li, Jian Zhang, Qiang Wu, Yongshun Gong, Jinfeng Yi, and Christina Kirsch. In KDD 2019
DTWNet: a Dynamic Time Warping Network
Xingyu Cai, Tingyang Xu, Jinfeng Yi, Junzhou Huang, and Sanguthevar Rajasekaran. In NeurIPS 2019
Fast Unsupervised Location Category Inference from Highly Inaccurate Mobility Data
Jinfeng Yi, Qi Lei, Wesley M. Gifford, Ji Liu, Junchi Yan, and Bowen Zhou. In SDM 2019
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
Pin-Yu Chen, Yash Sharma, Huan Zhang, Jinfeng Yi, and Cho-Jui Hsieh. In AAAI 2018
Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning
Hongge Chen, Huan Zhang, Pin-Yu Chen, Jinfeng Yi, and Cho-Jui Hsieh. In ACL 2018
Random Warping Series: A Random Features Method for Time-Series Embedding
Lingfei Wu, Ian En-Hsu Yen, Jinfeng Yi, Fangli Xu, Qi Lei, and Michael Witbrock. In AISTATS 2018
Is Robustness the Cost of Accuracy? - A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
Dong Su, Huan Zhang, Hongge Chen, Jinfeng Yi, Pin-Yu Chen, Yupeng Gao. In ECCV 2018
Query-Efficient Black-Box Attack by Active Learning
Pengcheng Li, Jinfeng Yi, and Lijun Zhang. In ICDM 2018
Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
Tsui-Wei Weng, Huan Zhang, Pin-Yu Chen, Jinfeng Yi, Dong Su, Yupeng Gao, Cho-Jui Hsieh, and Luca Daniel. In ICLR 2018
Self-weighted Multiple Kernel Learning for Graph-based Clustering and Semi-supervised Classification
Zhao Kang, Xiao Lu, Jinfeng Yi, and Zenglin Xu. In IJCAI 2018
Identify Susceptible Locations in Medical Records via Adversarial Attacks on Deep Predictive Models
Mengying Sun, Fengyi Tang, Jinfeng Yi, Fei Wang, and Jiayu Zhou. In KDD 2018
Diverse Few-Shot Text Classification with Multiple Metrics
Mo Yu, Xiaoxiao Guo, Jinfeng Yi, Shiyu Chang, Saloni Potdar, Yu Cheng, Gerald Tesauro, Haoyu Wang, and Bowen Zhou. In NAACL 2018
Adaptive Negative Curvature Descent with Applications in Non-convex Optimization
Mingrui Liu, Zhe Li, Xiaoyu Wang, Jinfeng Yi, and Tianbao Yang. In NeurIPS 2018
ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training Substitute Models
Pin-Yu Chen, Huan Zhang, Yash Sharma, Jinfeng Yi, and Cho-Jui Hsieh. In AISec 2017
Improved Dynamic Regret for Non-degenerate Functions
Lijun Zhang, Tianbao Yang, Jinfeng Yi, Rong Jin, and Zhi-Hua Zhou. In NIPS 2017
Scalable Demand-Aware Recommendation
Jinfeng Yi, Cho-Jui Hsieh, Kush R. Varshney, Lijun Zhang, and Yao Li. In NIPS 2017
Stochastic Optimization for Kernel PCA
Lijun Zhang, Tianbao Yang, Jinfeng Yi, Rong Jin, and Zhi-Hua Zhou. In AAAI 2016
Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient
Tianbao Yang, Lijun Zhang, Rong Jin, and Jinfeng Yi. In ICML 2016
Efficient distance metric learning by adaptive sampling and mini-batch stochastic gradient descent (SGD)
Qi Qian, Rong Jin, Jinfeng Yi, Lijun Zhang, and Shenghuo Zhu. Machine Learning 2015
An Efficient Semi-Supervised Clustering Algorithm with Sequential Constraints
Jinfeng Yi, Lijun Zhang, Tianbao Yang, Wei Liu, and Jun Wang. In KDD 2015
Privacy and Regression Model Preserved Learning
Jinfeng Yi, Jun Wang, and Rong Jin. In AAAI 2014
A Single-Pass Algorithm for Efficiently Recovering Sparse Cluster Centers of High-dimensional Data
Jinfeng Yi, Lijun Zhang, Jun Wang, Rong Jin, and Anil K. Jain. In ICML 2014
Efficient Algorithms for Robust One-bit Compressive Sensing
Lijun Zhang, Jinfeng Yi, Rong Jin. In ICML 2014
Inferring Users' Preferences from Crowdsourced Pairwise Comparisons: A Matrix Completion Approach
Jinfeng Yi, Rong Jin, Shaili Jain, and Anil K. Jain. In HCOMP 2013
Online Kernel Learning with a Near Optimal Sparsity Bound
Lijun Zhang, Jinfeng Yi, Rong Jin, Ming Lin, and Xiaofei He. In ICML 2013
Semi-supervised Clustering by Input Pattern Assisted Pairwise Similarity Matrix Completion
Jinfeng Yi, Lijun Zhang, Rong Jin, Qi Qian, and Anil K. Jain. In ICML 2013
Online Kernel Selection: Algorithms and Evaluations
Tianbao Yang, Mehrdad Mahdavi, Rong Jin, Jinfeng Yi, and Steven C. H. Hoi. In AAAI 2012
Robust Ensemble Clustering by Matrix Completion
Jinfeng Yi, Tianbao Yang, Rong Jin, Anil K. Jain, and Mehrdad Mahdavi. In ICDM 2012
Stochastic Gradient Descent with Only One Projection
Mehrdad Mahdavi, Tianbao Yang, Rong Jin, Shenghuo Zhu, and Jinfeng Yi. In NIPS 2012
Semi-Crowdsourced Clustering: Generalizing Crowd Labeling by Robust Distance Metric Learning
Jinfeng Yi, Rong Jin, Anil K. Jain, Shaili Jain, and Tianbao Yang. In NIPS 2012