Yang Li
Welcome to my homepage! I'm a pre-tenure associate professor at Tsinghua Berkeley Shenzhen Institute (TBSI) and Tsinghua-Shenzhen Interntional Graduate School, Tsinghua University.
My overall research interest is developing efficient learning algorithms for uncertain, heterogeneous data. Most of my works exploit the intrinsic, shared structures in collections of data, to solve challenges in collective analysis of spatial trajectories, multi-modal learning and transfer learning. Applications of my research cover a wide range of problems, including
image-based computer vision and medical image processing
mobility computing and smart transportation
interactions of mobile agents
My current work focuses on incorporating information theory and optimization concepts into transfer learning, where we aim to answer fundamental questions such as how transferable are features between different tasks and domains, and how to learn robust models across many small domains.
I obtained my PhD. degree in Computer Science from Stanford University in 2017, advised by Leonidas Guibas. My dissertation explores how to find shared structures in large GPS trajectories under uncertainty, and how the shared structures can be used to solve challenging problems. See the Research page for details about my past projects. I was also a contributor to the KINARI project.
News
(2024/7) We are organizing the 2024 Workshop on Learning & Information Theory in Shenzhen, China on August 19-20. Check out the website for more information!
(2024/2) I gave an AI seminar lecture on Transferability Guided Transfer Learning at The Hong Kong University of Science and Technology (Guangzhou)
(2023/10) I visited the CS Department at UT Austin and collaborated on a topological data analysis project with Prof. Qixing Huang's group.
(2023/7) We are hosting a Volunteer Behavior Prediction Data Challenge at IEEE MLSP 2023. See the Challenge Website for details!
(2023/6) I gave a guest talk on Transferability Guided Transfer Learning at the National and Kapodistrian University of Athens.
(2023/6) Congratulations to the first Ph.D. graduate of my group Yang Tan and to master graduates Wanda Li, Guanzi Chen and Yongchi Zhu!
(2023/5) Our new inititive, Workshop on Learning and Information Theory (WOLIT’23) is open for registration! We are also looking for student poster submissions.
(2022/7) The 4th TBSI Workshop on Information Theory (TBSI-WOLT) will be held in Shenzhen, Aug 7-9, 2022. We are also looking for Student Poster Session submissions on all areas of information and data science.
(2022/6) Congratulations to Yicong Li (MS’19) and Jingge Wang (MS’19) as the first two alumni in my group! They will be studying in the Ph.D. programs at Harvard and at TBSI, respectively.
(2022/3) Our paper “Optimising Self-organized Volunteer Behaviors during COVID-19 Pandemic” is now open access on the Nature website. Check out the project website for the code and interactive demo.
(2021/12) I gave a guest talk on Measuring Transferability in Transfer Learning at Shenzhen Institute of Advanced Technolog, Chinese Academy of Sciences
(2021/5) Come join the 3rd TBSI Workshop on Information Theory (TBSI-WOLT) in Shenzhen, China, July 5-7, 2021. Registration will be open soon, stay tuned!
(2020/8) I helped organize the 2nd TBSI Workshop on Information Theory (TBSI-WOLT) in Shenzhen, China, July 20-22, 2020. Checkout our Press Release!
(2020/7) I will be co-chairing the first TBSI Workshop on Data Science (TBSI-WODS) in Shenzhen, China, on Dec 17-19, 2019.
(2019/9) I gave an oral presentation at ICIP 2019, Taiwan on An Information-Theoretic Metric to Transferability in Task Transfer Learning
(2019/6) I gave a talk at Texas A&M University on Using Maximum Correlation for Transferability Estimation and Multi-Modal Learning
Contact
Email:
Address:
Information Building, Rm 1108A
Tsinghua Shenzhen International Graduate School
Shenzhen, Guangdong, China (518055)