Xiaofeng Cao
Home
Brief Biography
Dr. Xiaofeng Cao is currently an Associate Professor at School of Artificial Intelligence in Jilin University(JLU).
He received the PhD degree from Australian Artificial Intelligence Institute(AAII),
University of Technology Sydney (UTS) (QS #90, 2024), and supervised by
Prof. Ivor W. Tsang, where
the AAII was ranked Top#1 AI center in Australia, and Top#10 in the world, and the CS of UTS was ranked top #11 in ARWU 2021.
His research interests include PAC Learning Theory/Generalization Analysis, Theoretical Active Learning, Non-Euclidean Geometry/Manifold Optimization,
Machine Teaching/Black-Box Solving, Convex Optimization/Non-Convex Approximation, etc.
During the summer and winter of 2023,
Dr. Cao has been a visiting scholar at the Hong Kong University of Science and Technology , and supervised by Prof. James T. Kwok.
I am leading a "Machine Perceptron Group" with more than 20 PhD and Master students. I am always looking for self-motivated PhD/RA/Visiting/Master students. Please send me an email to query the detail.
欢迎同学们报考人工智能学院2023级硕士研究生和博士研究生保送！注：985本科生可直博保送！
News:
2024.05: Our work about geometry optimization on graphs was accepted by TNNLS!
2024.05: Our work about transductive optimization on reward inference was accepted by TKDE!
2024.05: Our work about Convex-Concave Loss optimization was accepted by ICML 2024!
2024.04: Our works about graph kernel and zero-shot generalization are accepted by IJCAI 2024!
2024.02: Visit the CFAR, and give a talk!
2024.01: Our work about black-box adversarial was accepted by ICLR 2024!
2023.12: Give a talk at Shenzhen Artificial Intelligence Society！
2023.11: Visit HKUST again!
2023.010: Give a presentation at MLA 2023, Nanjing!
2023.09:Our work about non-parametric optimization of multi-learner teaching was accepted by NeurIPS 2023!
2023.08: The hyperbolic autonomous driving research work in collaboration with colleagues from the University of Oulu and Stanford University was accepted by IEEE Transactions on Intelligent Transportation Systems!
2023.08: We accept one paper about over-smoothing from TKDE!
2023.07: Give a talk at INNOHK！
2023.07: Invited to serve as ECAI2023/ACML2023/WSDM2023/AAAI2024 Program Committee!
2023.06: My work on NP approximation optimization was accepted by IEEE T-PAMI!
2023.06: I served as a PC of MLJ-ACML SI!
2023.06: Give a talk at ShanghaiTech！
2023.06: We accept one paper from ECML 2023!
2023.04: We accept two papers from ICML 2023!
2023.04: I serve as a PC for ECML 2023!
Research
My current research interest:
PAC Learning Theory/Generalization Analysis Theoretical Active Learning Non-Euclidean Geometry/Manifold Optimization Machine Teaching/Black-Box Solving Convex Optimization/Non-Convex Approximation
Submissions Under Review/Revision
“ Black-box Generalization of Machine Teaching,”
X. Cao, Y. Guo, I. W. Tsang, and James T. Kwok,
Journal of Machine Learning Research, revision. “A Survey of Learning on Small Data,”
X. Cao, W. Bu, J. Huang, Y. Chang, and I. W. Tsang,
ACM Computing Surveys, review.
Selected Recent Publications
Transductive Reward Inference on Graph
Bohao Qu, Xiaofeng Cao, Qing Guo, Chang Yi, Ivor W.Tsang, and Chengqi Zhang
IEEE Transactions on Knowledge and Data Engineering Refining Euclidean Obfuscatory Nodes Helps: A Joint-Space Graph Learning Method for Graph Neural Networks
Zhaogeng Liu, Feng Ji, Jielong Yang, Xiaofeng Cao, Muhan Zhang, Hechang Chen, and Yi Chang.
IEEE Transactions on Neural Networks and Learning Systems Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss,”
Zhenlong Liu, Lei Feng, Huiping Zhuang, Xiaofeng Cao, Hongxin Wei
International Conference on Machine Learning (ICML 2024) Deep Hierarchical Graph Alignment Kernels
S. Tang, H. Tian, X. Cao, W. Ye
The 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024. Dual Expert Distillation Network for Generalized Zero-Shot Learning
Z. Rao, J. Guo, X. Lu, J. Liang, J. Zhang, H. Wang, K. Wei, X. Cao
The 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024. IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
Yue Cao, Tianlin Li, Xiaofeng Cao, Ivor Tsang, Yang Liu, Qing Guo
Twelfth International Conference on Learning Representations, ICLR 2024. Nonparametric Teaching for Multiple Learners,
Chen Zhang, Xiaofeng Cao*, Weiyang Liu, Ivor Tsang, James Kwok,
Thirty-seventh Conference on Neural Information Processing Systems, NeurIPS 2023. Hyperbolic Uncertainty Aware Semantic Segmentation.
Bike Chen, Wei Peng, Xiaofeng Cao, Röning Juha,
IEEE Transactions on Intelligent Transportation Systems, 2023. Enhancing Locally Adaptive Smoothing of Graph Neural Networks via Laplacian Node Disagreement,
Yu Wang, Liang Hu, Xiaofeng Cao*, Yi Chang,Ivor W. Tsang,
IEEE Transactions on Knowledge and Data Engineering, 2023. “Data-Efficient Learning via Minimizing
Hyperspherical Energy,”
X. Cao, Weiyang Liu, and I. W. Tsang,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023. DualMatch: Robust Semi-Supervised Learning with Dual-Level Interaction.
Cong Wang#, Xiaofeng Cao#*, Lanzhe Guo, Zenglin Shi.
Joint European Conference on Machine Learning 2023. Nonparametric Iterative Machine Teaching,
Chen Zhang, Xiaofeng Cao*, Weiyang Liu, Ivor Tsang, James Kwok,
The 40th International Conference on Machine Learning (ICML 2023). - Out-of-Distribution Generalization of Federated Learning via Implicit Invariant Relationships,
Yaming Guo#, Kai Guo#, Xiaofeng Cao*, Tieru Wu*, Yi Chang,
The 40th International Conference on Machine Learning (ICML 2023).
Distribution Matching for Machine Teaching,
Xiaofeng Cao, Ivor W. Tsang.
IEEE Transactions on Neural Networks and Learning Systems, 2023. “Distribution Disagreement via Lorentzian Focal Representation,”
X. Cao, and I. W. Tsang,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, [PDF][Code]. “Shattering Distribution for Active Learning,”
X. Cao, and I. W. Tsang,
IEEE transactions on neural networks and learning systems, [PDF][Code]. “Cold-Start Active Sampling via γ-Tube,”
X. Cao, and I. W. Tsang,
IEEE transactions on Cybernetics, 2021, [PDF][Code]. “Multidimensional balance-based cluster boundary detection for high-dimensional data,”
X. Cao, B. Qiu, X. Li, Z. Shi, G. Xu, J. Xu,
IEEE transactions on neural networks and learning systems, 2018, [PDF][Code]. “Crowd counting with deep negative correlation learning,”
Z. Shi, L. Zhang, Y. Liu, X. Cao, Y. Ye, M. M. Cheng, G. Zheng,
Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, [PDF][Code]. “Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation”,
X. Xu, I. W. Tsang, X. Cao, R. Zhang, C. Liu,
Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2020, [PDF][Code].
Students
Chen Zhang, PhD student (1 theoy manuscript, Machine Teaching, review in NIPS 2022) Yaming Guo, Master student (1 theoy manuscript, Active Learning Theory, review in JMLR) Yang Tao, Master student (1 theoy manuscript, Manifold Learning, Domain Adaption, review in NIPS 2022) Weixin Bu, Master student (1 survey, ready to submit to T-PAMI) Yu Wang, PhD student (1 optimization manuscript, Graph Neural Networks, ready to submit to TKDE) Kai Guo, PhD student (2 manuscripts on Graph Neural Networks) Jiaoyan Zhao, Co-supervised PhD student (2 manuscripts on feature selection) Cong Wang, Master student (Semi-Supervised Learning) Tianao Wang, Master student (Meta-Learning) Yunlong Li, Master student (Meta-Learning) Yadong Sun, Master student, 2022 Jiateng Li, Master student, 2022 Kaiwen Zheng, Master student, 2022 Ao Xu, Master student, 2022 Junjia Du, Undergraduate student, Out-of-Distribution Detection
|