About me

Zhilin Zhao is currently a Postdoctoral Fellow at Data Science Lab, Macquarie University, led by Prof. Longbing Cao. After earning his Ph.D. degree from the University of Technology Sydney (UTS) in 2022, where he was co-supervised by Prof. Longbing Cao and Prof. Philip S. Yu, he served as a Postdoctoral Fellow at UTS for a year. Prior to his doctoral studies, he completed his B.S. and M.S. degrees at the School of Data and Computer Science, Sun Yat-Sen University (SYSU), China, under the supervision of Prof. Chang-Dong Wang. He was honored with the Outstanding Undergraduate Student of SYSU Award in 2016 and the Outstanding Graduate Student of Canton Award in 2018.

Research

My current research focuses on generalization analysis, out-of-distribution detection, and distribution discrepancy estimation.

Representative Publications

• Zhilin Zhao and Longbing Cao, “R-divergence for Estimating Model-oriented Distribution Discrepancy,” in NeurIPS, 2023. [paper]
• Zhilin Zhao, Longbing Cao, and Kun-Yu Lin, “Revealing the Distributional Vulnerability of Discriminators by Implicit Generators,” in IEEE Trans. Pattern Anal. Mach. Intell., 2023. [paper]
• Zhilin Zhao, Longbing Cao, and Kun-Yu Lin, “Supervision Adaptation Balancing In-Distribution Generalization and Out-of-Distribution Detection,” in IEEE Trans. Pattern Anal. Mach. Intell., 2023. [paper]
• Zhilin Zhao, Longbing Cao, and Kun-Yu Lin, “Out-of-Distribution Detection by Cross-Class Vicinity Distribution of In-Distribution Data,” in IEEE Trans. Neural Networks Learn. Syst., 2023. [paper]
• Zhilin Zhao, Longbing Cao, and Chang-Dong Wang, “Gray learning from non-iid data with out-of-distribution samples,” in IEEE Trans. Neural Networks Learn. Syst., 2023.
• Zhilin Zhao and Longbing Cao, “Dual Representation Learning for Out-of-Distribution Detection,” in Trans. Mach. Learn. Res., 2023. [paper]