Associate Professor, Tsinghua Shenzhen International Graduate School
2 papers at NeurIPS 2025
We propose a theoretical framework based on asymptotic analysis to determine optimal sample transfer quantities in multi-source transfer learning, yielding an efficient algorithm (OTQMS) that enhances accuracy and data efficiency.
With an intention to better exploit the task relationships for continual learning, we propose a transferability-based task embedding named H-embedding and present a hypernet under its guidance.
